Speech_Recognition
-
Ruby-ASR: Evidence-Preserving Supervision for Joint Orthographic and Lexical-Reading Recognition
2026-09-23 03:28:08Hao Shi, Yun Liu, Xuehao Yang, Jun Liu, Chuanbo Hua, Xuanjun Chen, Lianbo Liu, Shiao Zhu, Zixiong SuAbstract
Conventional Japanese automatic speech recognition (ASR) is supervised by an orthographic transcript, although the same written form can correspond to different lexical readings realized in speech. Such utterances receive an identical target, so their reading distinction is absent from the supervision interface and cannot be recovered reliably by post-hoc text-only grapheme-to-phoneme conversion. We present Ruby-ASR, which refines the conventional target into a span-bound orthographic--lexical-reading sequence. Unlike separate full-sentence orthographic and phonological outputs, the ruby representation locally binds each written span to its realized reading and permits deterministic recovery of both views. We instantiate the target under subtitle-style and verbatim-style transcription conventions using a Qwen3-ASR backbone; a mora-level CTC objective provides auxiliary monotonic reading supervision. The experimental results across five Japanese benchmarks show that refining the recognition target can improve lexical-reading recovery without sacrificing readable orthographic transcription. We release the checkpoints and inference code.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27289
PDF
-
Quieter Than the Room: Representation Drift and Task Robustness in Speech Encoders
2026-09-23 00:58:15Vsevolod Kovalev, Pranay ManochaAbstract
Non-speech interference can change a speech representation without causing comparable task loss. We test eight frozen encoders on four tasks, adding non-speech sounds throughout recordings, during speech, or in pauses. Under whole-recording interference, embedding drift tracks task loss across seven sounds, with mean Spearman correlations of 0.81-0.88. Moving the same sound between speech and pauses changes this pattern. At quiet to moderate levels, pause interference produces larger drift, while speech interference usually causes greater loss on intent recognition, speaker verification and speech recognition. Emotion recognition shows a weaker placement effect. Pause interference also changes speech-frame representations beyond the injected region. Even below the estimated recording background, interference can change embeddings as much as repeated speech takes do. Drift helps rank the effects of different sounds, but larger drift does not consistently indicate greater task loss.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27195
PDF
-
NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task
2026-09-22 21:37:54Peter Sullivan, Bashar Talafha, Ahmed Ashraf, Fethi Bougares, Haroun Elleuch, Chiyu Zhang, AbdelRahim Elmadany, Youssef Mohamed, Salima Mdhaffar, Yannick Est\`eve, Mohamed Elhoseiny, Hamzah Luqman, Nizar Habash, Muhammad Abdul-MageedAbstract
NADI 2026 is the seventh edition of the Nuanced Arabic Dialect Identification (NADI) shared task series and the second dedicated to multidialectal Arabic speech processing. This edition comprises five tasks and eight subtasks spanning Automatic Speech Recognition (ASR), Spoken Dialect Identification (SDID), Text-to-Speech (TTS), Spoken Language Translation (SLT), and Spoken Language Understanding (SLU). NADI 2026 emphasizes realistic evaluation through low-bandwidth, mixed-dialect, code-switched, out-of-domain, and zero-shot settings, while introducing TTS, SLT, and SLU to the series for the first time. The shared task attracted 21 participating teams from at least 13 countries, with 48 test-phase submissions and 14 submitted system-description papers. Results show that out-of-domain generalization remains a major bottleneck and highlight the effectiveness of recent Arabic-specialized speech models, multimodal dialect identification approaches, and ensemble methods. Overall, NADI 2026 provides a broader and more challenging benchmark for robust Arabic dialect speech processing.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27086
PDF
-
From Reliable Text to Real Voices: Trust-Aware Progressive Adaptation for Low-Resource TTS
2026-09-22 09:56:09Jiayi Lu, Yizhong Geng, Jinghan Yang, Tianhan Jiang, Boxun An, Yingming Gao, Ya LiAbstract
Low-resource text-to-speech (TTS) adaptation is constrained by scarce paired data and costly manual transcription. Existing fixed-voice TTS systems can provide relatively accurate pronunciation, but their synthetic speech offers limited speaker diversity and may exhibit flat prosody. Real recordings provide natural prosody and diverse voices, yet their automatic speech recognition (ASR) pseudo-labels may contain transcription errors. We find that supervision order affects content accuracy and speaker similarity. We propose trust-aware progressive adaptation: synthetic-to-real adaptation first establishes text-speech correspondences, then restores reference-speaker control using real speech. Transcript-agreement weighting uses agreement between two fixed ASR systems as a proxy for pseudo-label reliability to limit noisy supervision. Experiments with FireRedTTS3 on Burmese and Lao and OmniVoice on Burmese show improved content accuracy with high naturalness and competitive speaker similarity. Jointly considering supervision order and pseudo-label reliability when combining synthetic and real speech offers a practical path to zero-shot voice cloning in low-resource languages with less manual transcription. Audio demos are available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.25951
PDF
-
LLM-based Conversational AI Knowledge Assistant for MyBuddy Humanoid Robot
2026-09-21 15:11:06Hanxiao ChenAbstract
Humanoid robots are increasingly being popular and developed for human-centered applications, yet their ability to provide intelligent conversations and natural interactive knowledge assistance remains constrained by traditional rule-based dialogue systems, pre-defined responses and limited knowledge repositories. Large language models (LLMs) have emerged as a powerful foundation for enabling natural, adaptive, and context-aware Human-Robot Interaction (HRI), which provides a significant opportunity to address such limitations by enabling robots to understand natural speech language, reason over complicated queries, maintain high-quality conversational context, and generate knowledge-rich responses. In this work, we originally present and implement an LLM-based versatile Conversational AI Knowledge Assistant for the Raspberry-Pi-powered 13-Axis MyBuddy humanoid robot, which integrates LLM-driven language understanding and AI reasoning with real-time speech recognition, knowledge retrieval via extensible access of internet engines (e.g., Wikipedia, arXiv), flexible dialogue management, and natural speech synthesis to enable much more intelligent multi-turn continuous conversations and advanced emotional-support Human-Robot Interaction.
Abstract (translated)
URL
https://arxiv.org/abs/2609.24742
PDF
-
Vimarsha: Faithful ASR Evaluation for Indian Languages with Demographic Diversity, In-the-Wild Audio and Spelling Variations
2026-09-21 07:14:46Kaushal Santosh Bhogale, Srija Anand, Sadakopa Ramakrishnan Thothathiri, Tahir Javed, Sshubam Verma, Mitesh M. KhapraAbstract
Evaluation benchmarks for Indian language automatic speech recognition (ASR) suffer from two systematic biases: optimistic scores from clean, controlled audio conditions, and pessimistic scores from overly rigid transcription standards that penalize valid linguistic variations. We introduce Vimarsha, a 100-hour benchmark spanning all 22 scheduled Indian languages, designed to address both distortions. Vimarsha combines demographically diverse on-field recordings with carefully mined in-the-wild audio selected for acoustic difficulty, alongside a lattice of variations framework that encodes multiple valid transcriptions per utterance. Evaluations of 10 state-of-the-art ASR models reveal substantial shifts in model rankings under realistic conditions, geographic and demographic performance disparities, and systematic failure modes across speaking rates and acoustic environments.
Abstract (translated)
URL
https://arxiv.org/abs/2609.24199
PDF
-
HaikuS2S: A Cascaded System For Responding In Verse
2026-09-20 23:47:30Devangi Sharma, Sophia Judicke, Glenda Tan, Conrad Schaumburg, Shinji WatanabeAbstract
Expressive speech synthesis has advanced through prosody modeling, yet generating structured poetic speech, such as haiku, remains challenging. Prior work on prosody transfer improves expressiveness, and fine-tuned poetry TTS (text-to-speech) systems capture verse intonation. However, these models do not model haiku's 5-7-5 syllable structure or line-ending pauses. We present a cascaded system, HaikuS2S, combining ASR (automatic speech recognition), LLM (large language model)-generated haiku, and TTS fine-tuning on both prose and custom haiku datasets. Our evaluation focuses on emotion similarity, speech quality, and prosody alignment. In our experiments, we see that our prosody and tonal alignment improve significantly with our fine-tuned systems, particularly the one trained on both general poetry and haiku. We also see that we maintain similar emotion similarity scores across all systems.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23951
PDF
-
Federated Multilingual Speech-LLMs: Architecture and Aggregation Strategy Benchmarking
2026-09-20 19:23:15Jordi Luque, Aleix Sant, Fernando L\'opezAbstract
We present a comprehensive benchmark of Federated Learning (FL) for multilingual Automatic Speech Recognition (ASR), evaluating four Speech-LLM architectures on the Multilingual LibriSpeech dataset. We compare FedAvg and FedProx across frozen and unfrozen encoder configurations, demonstrating that optimized learning rates are critical for performance. Specifically, independently tuning the learning rates for the speech encoder, connector, and decoder yields the lowest error rates, with full three-component adaptation (LoRA for encoder and decoder, full training for the connector) producing the best FL results. We observe that FedProx efficacy is architecture-dependent, providing notable advantages in multilingual pre-trained architectures (e.g., EuroLLM over TinyLlama when keeping the encoder fixed); this indicates that LLM backbone capacity plays a key role in mediating resilience to heterogeneous data distributions. These findings offer concrete design guidance for deploying multilingual Speech-LLMs in privacy-sensitive, distributed environments.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23825
PDF
-
Beyond Encoder Fusion: Multi-View Discrete Token Augmentation for LLM-Based ASR
2026-09-20 10:19:46Paul Mo\"ise Gangbadja, Mickael Rouvier, Fabrice Lef\`evreAbstract
Discrete speech tokens provide a compact interface between speech encoders and large language models for automatic speech recognition, but single-tokenization systems remain sensitive to the chosen encoder. We propose multi-view discrete token augmentation, a simple strategy that augments each training utterance by generating alternative token sequences from fixed SSL encoders, such as HuBERT, WavLM, and MMS-300M. These tokenizations are treated as complementary training views for a shared LLM decoder, exposing it to more diverse discrete speech representations without requiring multi-encoder inference. At test time, the model can operate with a single encoder. On LibriSpeech, the approach consistently improves all encoders over independently trained baselines, with WavLM reaching 3.30% WER on test-clean and 8.13% on test-other. Budget-matched controls show that the gains come from encoder diversity rather than data volume. ROVER over multi-view hypotheses further improves WER to 3.03% and 7.38%.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23525
PDF
-
Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track~1 System for the NVVSpeech Challenge
2026-09-20 08:45:31Shangyue Jia, Jingru Ma, Yangzhuo Li, Daoping Luo, Bowen Tian, Hanchen Lu, Wenze Ren, Yunxiang Chen, Houdun Liu, Shuo Feng, Lei Xie, Liumeng XueAbstract
Non-verbal vocalizations (NVVs) carry important paralinguistic information but are often omitted by conventional automatic speech recognition (ASR) systems. The ISCSLP NVVSpeech Challenge requires joint transcription of lexical content and 16 NVV categories under limited and highly imbalanced supervision. We present a data-centric NVV-aware ASR pipeline based on cross-dataset label harmonization and a two-stage sampling schedule. We map heterogeneous source labels to the official taxonomy and exclude samples without a reliable mapping. Our schedule first uses square-root category sampling to moderate the long-tailed distribution and then applies uniform-category fine-tuning. On a fixed local validation split, square-root category sampling performs best among the tested single-stage settings. The final two-stage system obtains an official score of 63.86 and ranks fourth in Track 1.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23462
PDF
-
ParA-LLM: A Unified Approach to Paralinguistic and Acoustic Speech Understanding
2026-09-19 05:08:58Nishit Anand, Jiaqi Su, Ke Chen, Yunyun Wang, Dinesh Manocha, Ramani Duraiswami, Rithesh Kumar, Zeyu JinAbstract
Recent advances in Audio LLMs have achieved human-level speech recognition, yet existing systems struggle to capture paralinguistic aspects such as speaker traits, expressive variations, and environmental acoustic conditions. To address this, we design a framework of 22 paralinguistic characteristics and create a dataset of over 1.2M Audio-QA pairs. We develop ParA-LLM, trained with a two-stage curriculum: first on single-attribute questions to build foundational knowledge, then on multi-attribute questions for joint reasoning over speaker and acoustic characteristics. We also release ParA-Bench, a benchmark of 6,000 multiple-choice questions across speaker-speech, acoustic, and mixed categories, where frontier models like GPT-4o-Audio achieve only 36% accuracy. ParA-LLM surpasses state-of-the-art Audio LLMs like GPT-4o-Audio by 7.5% on ParA-Bench, with additional gains of 1.13% on MMAU-Pro Speech and 7.49% on MMAR Speech.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22771
PDF
-
NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities
2026-09-18 16:27:22Jagadeesh Balam, Travis Bartley, Edresson Casanova, Sanjay Chauhan, Chen Chen, Zhehuai Chen, Zijia Chen, Francesco Ciannella, Slyne Deng, Mikyas Desta, Harishchandra Dubey, Slim Essid, Nourchene Ferchichi, Boris Ginsburg, Mariana Graterol Fuenmayor, Negar Habibi, Kevin Hu, Anand Joseph, Viraj Karandikar, Myungjong Kim, Viacheslav Klimkov, Seelan Lakshmi Narasimhan, Lily Lee, Jason Li, Eileen Long, Ameya Mahabaleshwarkar, Aditya Malte, Adi Margolin, Sasha Meister, Valentin Mendelev, Oluwatobi Olabiyi, Ankita Pasad, Yifan Peng, Elena Rastorgueva, Jayda Ritchie, Jason Roche, Nikhil Srihari, Yuanhang Su, Yoshi Suhara, Viet Anh Trinh, Jinhan Wang, Piotr Zelasko, Hui Wang, Puhui Meng, Chaosen Zhang, Yunsheng Liu, Shawn Wang, Wenjing Li, Zhonglei HeAbstract
We introduce NemotronLabs VoiceChat, an open full-duplex speech-to-speech model with native tool-calling capabilities. NemotronLabs VoiceChat combines a streaming speech encoder and decoder-only language model with parallel specialized output streams for agent text and structured function calls, an auxiliary RNN-T branch for incremental user transcription, and a streaming TTS decoder. This design enables the model to listen, transcribe, reason, invoke tools, and speak within a unified streaming architecture while preserving the temporal behavior required for natural conversation. On Full-Duplex-Bench 1.0, NemotronLabs VoiceChat achieves the lowest pause-handling takeover rates among evaluated open-weight systems, 100\% takeover following user interruptions, and a 4.33/5 post-interruption response-quality score. On Full-Duplex-Bench 1.5, it resumes its response after user backchannels in 93\% of cases. NemotronLabs VoiceChat obtains a 55.1 normalized average on VoiceBench and, on Full-Duplex-Bench 3.0 (FDB 3.0), achieves 82.5\% tool-selection F1, while argument accuracy and end-to-end tool execution remain areas for improvement. These results demonstrate that full-duplex interaction, speech recognition and generation, general language capabilities, and external tool use can be integrated in a single open speech-to-speech model without sacrificing real-time conversational behavior.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21967
PDF
-
Rethinking Human-Aligned Evaluation: An Analysis of Semantic Metrics Beyond WER
2026-09-18 12:00:01Hritika Sharma, Thibault Ba\~neras-Roux, Alessandra Pinto, Petr Motlicek, Hyunggu Jung, Esa\'u Villatoro-Tello, Somang NamAbstract
Word Error Rate (WER), the most commonly used metric for Automatic Speech Recognition (ASR), treats every lexical deviation from the reference as equally costly, regardless of whether it changes meaning. This raises the question: does WER actually track how humans judge ASR transcript quality? We introduce HATS-en, an English dataset for human-centered ASR evaluation. Using this dataset, we benchmark lexical metrics against several configurations of BERTScore and SemDist, varying the language model, layer, and pooling strategy. We find that WER agrees least with human judgment among all metrics tested, that the best-performing SemDist configurations achieve the highest overall agreement, ahead of CER and BERTScore, and that no single model is best across settings. CER, despite its simplicity and low cost, remains remarkably close to these best configurations. In line with prior recommendations, our results support shifting ASR evaluation toward CER both for English and for morphosyllabic writing systems as it is a more interpretable and low-cost metric for what evaluation should actually capture, and using SemDist as a complementary evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21663
PDF
-
OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue
2026-09-18 08:15:34Haolin He, Yunfei Chu, Qi Chen, Wen Huang, Yuan Feng, Muzhi Zhu, Zheqi Dai, Haoning Xu, Dongchao Yang, Chunyat Wu, Zining Liang, Zhengxi Liu, Xiquan Li, Xie Chen, Xize Cheng, Qize Yang, Jin Xu, Qiuqiang KongAbstract
We define OmniVChat (Omni Video Chat) as the task of native audio-visual dialogue between a user and an omni model. In OmniVChat, omni models directly and simultaneously receive audio and video from a user and return text. The user's query is embedded in the audio and video, without a separate text question, external captioning, or speech recognition. Direct audio-visual input reduces external latency and computation while preserving perceptual cues. However, research on OmniVChat faces two constraints: data availability and evaluation. Recordings of people using their own devices are scarce. Furthermore, a good reply often needs to account for the user's surroundings, facial expressions, and nearby objects, and such responses can be expressed in many different ways, making keyword matching unreliable for evaluating reply quality. Recent progress in agent systems and video generation makes generation for comprehension viable, which means using synthesized dialogues for training and evaluation. Therefore, we present OmniVChat-Studio, a multi-agent data engine for synthesizing single- and multi-turn audio-visual dialogues. We use synthesized dialogues to build OmniVChat-Bench, an evaluation benchmark that evaluates omni models' basic dialogue abilities across five ability categories. We also present OmniVChat-RL, a reinforcement learning reward design that jointly targets reply correctness, efficiency, and style in OmniVChat. Training Qwen3-Omni-Instruct with OmniVChat-RL on synthesized dialogues improves its performance on both OmniVChat-Bench and the human-recorded OmniVChat-Bench-Human. These gains validate the reward design and show transfer to real-world dialogues in training and evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21465
PDF
-
Online Algorithms for Independent Low-Rank Matrix Analysis and Rank-Constrained Spatial Covariance Matrix Estimation Based on Maximum Weighted Likelihood Estimation
2026-09-18 01:02:59Yuto Ishikawa, Norihiro Takamune, Tomohiko Nakamura, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu KondoAbstract
Real-time multichannel speech extraction (MSE) under diffuse noise conditions is an important task with a wide range of applications, such as speech recognition and hearing aids. In this paper, we propose online algorithms for independent low-rank matrix analysis (ILRMA) and rank-constrained spatial covariance matrix estimation (RCSCME). Previously, we proposed a real-time extension of the RCSCME-based method: an MSE method based on ILRMA and RCSCME using the blockwise batch algorithm. However, it assumes that the spatial characteristics are stationary within a single batch, and thus, in dynamic situations where the target speaker moves, its performance may degrade. To address this problem, we derive the online algorithms for ILRMA and RCSCME in the following three steps. First, we formulate framewise cost functions for ILRMA and RCSCME on the basis of maximum weighted likelihood estimation. Second, we derive the update rules for the framewise cost functions on the basis of auxiliary-function techniques. These naive update rules are computationally costly for real-time execution on a practical machine. Thus, we finally derive the online algorithms by approximating some intermediate parameters with their estimates. Furthermore, we propose stabilization and further acceleration techniques for these online algorithms. In experiments, we simulate situations where a target speaker is stationary or moves and show that the proposed method achieves superior speech extraction performance compared with conventional methods. In addition, using real-world recorded signals, we demonstrate the effectiveness of the proposed method in practical scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21180
PDF
-
Talk to Me, Jarvis: An Open-Source Edge-Deployable Voice Assistant Framework for Autonomous Racecars
2026-09-17 21:51:03Daniel Henel, Frederik Werner, Alexander Langmann, Johannes BetzAbstract
Recent advances in large language models have improved their effectiveness as back-end components for voice assistants, particularly in intent understanding and context-aware input classification. However, online-hosted models introduce network dependency and variable inference latency, limiting their suitability for time-critical autonomous driving applications. In this work, we address these issues by developing Jarvis, an offline voice assistant for high-level behavioral commands of autonomous vehicles. Its architecture integrates speech recognition and synthesis with natural language command classification into a lightweight, local framework. Jarvis core component is a text-to-command classifier, built using a domain-specific fine-tuning of the Mistral 7B model, demonstrating low-latency inference. Our experimental evaluation demonstrates that our solution outperforms larger online-hosted models, achieving 97.63 % intent recognition accuracy with an average processing latency of 1.39 s, making it well-suited for operations requiring quick response times. To support further research and fine-tuning, we provide an open-source implementation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21109
PDF
-
The Hidden Cost of Digits: Number Normalization and WER in ASR Systems
2026-09-17 21:01:13Stanis{\l}aw Kacprzak, Mieszko Fra\'sAbstract
Modern automatic speech recognition (ASR) systems trained on extremely large datasets can produce transcripts with numbers written in Arabic numerals. This creates a need for fair comparison with models that output verbatim texts and proper processing of reference transcripts. Popular approaches often reduce text normalization to lowercase and remove punctuation, with no additional normalization applied to languages other than English. In this work, we analyze the impact of normalization of numerical expressions in the evaluation of ASR systems in various languages, using Polish as an example of a highly inflective language. We perform experiments on VoxPopuli and The Polish Parliamentary speech datasets and estimate word error rate (WER) differences for different text normalization approaches. We show that the difference due to the lack of number normalization in WER may be substantial - more than 2 percentage points, and often higher than the differences between systems in popular multilingual benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2609.21084
PDF
-
Model-Agnostic and Language-Agnostic Voice Pipeline Improvement for the Agriculture Domain
2026-09-17 14:50:12Aakash Singh, Lakshmi Pedapudi, Chandrashekar M S, Sanyam Singh, Naga Ganesh, Vineet SinghAbstract
FarmerChat is Digital Green's AI-powered agricultural advisory assistant for smallholder farmers, who access it in their own language through text, voice, or photographs. Voice is a critical channel for this population, yet field-recorded speech is challenging for general-purpose automatic speech recognition (ASR) because recordings frequently contain machinery noise, background media, competing speakers, and domain-specific agricultural vocabulary. These conditions disproportionately affect crop, pest, chemical, and quantity terms that carry the meaning of a farmer's query. We present a modular, model-agnostic pipeline for improving ASR quality in FarmerChat without fine-tuning or replacing the underlying ASR model. The pipeline combines gated audio enhancement, speaker diarization and target-speaker selection, ASR, domain-aware correction using a weighted agricultural lexicon, and a quality gate for detecting unreliable transcripts. Only the diarization stage is fine-tuned; all other stages use off-the-shelf models behind common interfaces. We evaluate the pipeline on human-annotated FarmerChat recordings in Hindi, Telugu, and Odia using word error rate (WER) and a domain-weighted error rate that gives greater importance to agricultural terminology. The largest improvements occur on multi-speaker recordings, where target-speaker selection prevents competing speech from entering the transcript. Across the full corpus, the pipeline reduces WER by 16-23% relative on three cloud ASR models and by 5% on an on-device model. On multi-speaker recordings, the reductions are 32-42% for the cloud models and 16% for the on-device model. All reported reductions are statistically significant. These results show that targeted preprocessing, speaker selection, and domain-aware post-processing can substantially improve agricultural speech transcription while preserving the underlying ASR model.
Abstract (translated)
URL
https://arxiv.org/abs/2609.20504
PDF
-
Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data
2026-09-17 07:16:45Rui Hu, Zhenpeng Zhan, Xiaolong LinAbstract
Grapheme-to-phoneme (G2P) conversion turns raw text into its phonemic form and is an essential part of both text-to-speech (TTS) and automatic speech recognition (ASR) systems. It is required to be fast, stable and context-aware. For unsegmented languages such as Japanese, G2P additionally couples word segmentation with highly context-dependent polyphone disambiguation, and the scarcity of accurately annotated data remains a bottleneck. In this paper, we present a context-aware neural G2P method that scores paths of a discriminative conditional random field (CRF) over a word lattice constructed from dictionaries. To tackle data scarcity, we utilize large language models (LLMs) to generate more than 2 million sentences. Experimental results demonstrate that our method strongly outperforms conventional morphological analyzer-based methods and neural sequence models. On the Joyo-Kanji-Yomi benchmark, our method reaches 99.62% target word reading accuracy, 0.32% target word phoneme error rate (PER) and 0.14% sentence PER.
Abstract (translated)
URL
https://arxiv.org/abs/2609.19805
PDF
-
Multi-Teacher Distillation for Cross-Domain Streaming Electrolaryngeal Speech Encoding
2026-09-16 14:00:38Benedikt Mayrhofer, Enrique Orozco Olivares, Franz Pernkopf, Philipp Aichinger, Martin Hagm\"ullerAbstract
Self-supervised learning (SSL) has improved speech representations, yet performance degrades in pathological domains such as electrolaryngeal (EL) speech, and the computational footprint of SSL models limits their applicability in real-time, on-device deployment. We propose a multi-teacher knowledge distillation framework to train a lightweight, streaming content encoder that generalizes across healthy (HE) and EL speech. Two teachers are distilled progressively: a frozen SSL model providing discrete phonetic cluster targets from HE speech, and an EL-fine-tuned speech recognition model supplying continuous bottleneck feature targets. Evaluated via downstream speech recognition, our approach reduces the EL word error rate to 21.2%, compared to 39.3% for the strongest zero-shot SSL baseline. Among causal convolutional, Transformer, Conformer, and Mamba-based student architectures, a Mel-Conformer achieves the best combination of EL accuracy and computational efficiency. The final encoder contains 21.9,M parameters and runs at a real-time factor of 0.30 under ONNX Runtime on a single CPU core.
Abstract (translated)
URL
https://arxiv.org/abs/2609.18686
PDF
