Speech
-
SpectralBridge: Adding High-Frequency Capability to Large Audio-Language Models
2026-10-12 16:20:06Sergei Polezhaev, Saba Anjum, Michael GormishAbstract
Large audio-language models (LALMs) have become highly capable on a wide range of tasks spanning speech, music, and environmental sound. However, many modern LALMs resample input audio to 16 kHz mono, making all frequencies above 8 kHz unobservable. We present SpectralBridge, a lightweight extension that gives such a model access to the 8-16 kHz band by joining low- and upper-band representations with time-aligned paired cross-frequency attention. Applied to Audio Flamingo Next, the method trains only a small adapter and rank-8 LoRA modules, while leaving the original audio encoder, audio projector, and base language model frozen. SpectralBridge improves both zero-shot transfer and downstream fine-tuning: it raises zero-shot balanced accuracy on the ESC-50 audio classification dataset from 75.5 to 90.5, and when fine-tuned on Insect-10, a 10-way insect species task we construct from InsectSet459 recordings, under the same budget as a LoRA fine-tuned baseline, it reaches 55.4 balanced accuracy against the baseline's 26.2. On a benchmark where the answer depends only on the 8-16 kHz band, it gains 30 mAP over the frozen model. Erasing the upper-band stream from the trained model removes these gains, showing that they come from the high-frequency signal itself rather than from extra tokens or the adapted prompt format.
Abstract (translated)
URL
https://arxiv.org/abs/2610.17048
PDF
-
Understanding Personalization Gains in Whisper
Abstract
Whisper-style ASR models provide strong zero-shot transcription, but their residual errors are not evenly distributed across datasets, recording conditions, and metadata-based groups. We study when lightweight low-rank adaptation (LoRA) improves Whisper and whether observed gains require group-specific adapters. Across Common Voice, LibriSpeech, and VoxPopuli, we compare zero-shot Whisper, pooled LoRA, and group-specific LoRA under matched within-group splits. We find that adaptation is not uniformly beneficial: gains are concentrated in difficult Common Voice groups, are consistent on VoxPopuli, and largely disappear on low-error LibriSpeech. Crucially, pooled LoRA often matches, and sometimes clearly outperforms, group-specific LoRA. Gains over zero-shot should therefore be tested against matched pooled adaptation before being interpreted as evidence of personalization.
Abstract (translated)
URL
https://arxiv.org/abs/2610.17019
PDF
-
SarcasTraps: Effect of Sarcasm on Turkish Hate Speech Detection
2026-10-12 15:25:27Niyazi Ahmet Metin, Dilara Kek\"ull\"uo\u{g}luAbstract
Standard hate speech detection datasets often emphasize explicit harmful language, but directed harm can also be expressed indirectly, without clearly hateful wording. Sarcasm is one such form of indirect expression, as it can convey harmful intent through mock praise, exaggeration, humor, or apparent politeness. In this paper, we introduce SarcasTraps, a targeted external test set for analyzing the effect of sarcasm on Turkish hate speech detection. SarcasTraps contains 479 entries annotated along two dimensions: hate speech and sarcasm. We train classifiers using BERTurk and XLM-RoBERTa on two existing Turkish hate speech datasets and evaluate them on SarcasTraps, using it strictly as an external test set. We also evaluate GPT-4.1 and Llama-3.3-70B in a zero-shot setting on SarcasTraps. Results show that sarcasm substantially affects hate speech detection. Fine-tuned encoder models lose recall on sarcastic hate, while zero-shot LLMs maintain higher recall but suffer substantial precision drops on sarcastic examples. These findings show that both fine-tuned hate speech detectors and zero-shot LLMs struggle when sarcasm is involved, and SarcasTraps provides quantitative evidence of this challenge through a targeted Turkish test set. Due to the presence of sensitive and hateful language, SarcasTraps will be shared upon request for academic research purposes. Warning: This paper has examples from the dataset which contains offensive and hateful content towards groups of people.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16957
PDF
-
What Makes Codec Tokens Effective for Target Speaker Extraction? A Semantic-Acoustic Disentanglement Perspective
2026-10-12 14:27:24Wang Xiang, Bang Zeng, Ming LiAbstract
Target speaker extraction (TSE) aims to recover a target speaker's speech from a speech mixture using an enrollment utterance. Recent codec-based generative approaches formulate TSE as conditional speech token generation and achieve promising perceptual quality. However, most existing systems rely on unified codec tokens that entangle linguistic content, speaker characteristics, and acoustic details, forcing a single model to jointly handle target selection, content semantic, and acoustic reconstruction. In this paper, we investigate whether disentangled semantic-acoustic codec representations are better suited to TSE. We first show that simply replacing unified codec tokens with semantic-acoustic tokens is insufficient and can even degrade performance when both remain handled by a unified generative model. Motivated by this observation, we propose a task-aware discriminative-generative framework, where a discriminative branch extracts target-related semantic information, while a generative branch predicts coarse acoustic tokens and refines them under semantic guidance. This specialization separates what is said from how it sounds while coordinating both factors in a factorized codec space. Experiments on Libri2Mix show that our method reduces dWER from 0.388 to 0.118 compared with a unified-codec baseline, while maintaining competitive perceptual quality and speaker consistency. Ablation studies confirm that the gains arise from task-aware semantic-acoustic modeling rather than representation disentanglement alone.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16858
PDF
-
Unsupervised Data Drift Monitoring for Deployed Deepfake Speech Detectors
2026-10-12 14:08:25Luk\'a\v{s} Proke\v{s}, Vojt\v{e}ch Stan\v{e}k, Anton Firc, Kamil MalinkaAbstract
Deepfake speech detectors are typically evaluated as binary classifiers on fixed benchmarks, but deployed systems face evolving attacks, codecs, speakers, and recording conditions, with labels unavailable during operation. This makes it difficult to know when a detector operates in familiar conditions and can be relied on. We propose an unsupervised drift monitor that operates on the internal embeddings of a deployed detector. The monitor compares each input against bona fide and spoof references using regularized Mahalanobis distances. These distances define trusted, ambiguous, and novel regions of the detector embedding space, allowing unfamiliar inputs to be routed for review. We evaluate the monitor on four modern detectors on three datasets. The monitor raises alerts for dataset mismatches and substantially reduces the security-critical case of accepting deepfakes at the cost of reduced automatic coverage. The results also show that drift affects both classes: bona fide recordings can move away from the training reference, increasing alert rates even in in-domain settings. Our findings suggest that deployed deepfake speech detectors should be treated not only as a binary classification, but also as a reliability problem.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16826
PDF
-
LLM-HB: Language-Aware LLM-Guided Hotword Biasing for Code-Switching ASR
2026-10-12 11:00:40Yuxuan He, Genshun Wan, Pengcheng Li, Gongping Huang, Jianqing Gao, Yanmin QianAbstract
Code-switching (CS) speech, characterized by language alternation within a single utterance, is prevalent in multilingual communities and poses challenges to automatic speech recognition (ASR) due to rapid language transitions. We propose LLM-HB, a language-aware large language model-guided hotword biasing framework for code-switching ASR (CS-ASR). The framework incorporates a mixture-of-experts (MoE) adaptor and an auxiliary language prediction head to better capture and differentiate multilingual representations, while hotwords are injected through LLM-based prompting. Experiments on the ASRU2019 code-switching challenge test set demonstrate that LLM-HB achieves a 20.30% relative reduction in mixed error rate (MER) over the baseline, reaching 5.85% MER under a 15-distractor hotword setting. To the best of our knowledge, this is the first work to integrate LLM-guided biasing into code-switching ASR. We further release the extracted ASRU2019 hotword list to support future research.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16579
PDF
-
SyncReward: Human-Aligned Synchronization Reward for Audio-Visual Generation
2026-10-12 07:59:09Kaisi Guan, Ying Ba, Wenjing Wang, Xihua Wang, Chen Li, Jing Lyu, Ruihau SongAbstract
Recent years have witnessed rapid progress in joint audio--visual generation. However, audio--visual synchronization remains a challenge, as generated speech and sound often temporally misalign with visual events. A key bottleneck is the lack of human-annotated data, reliable evaluation benchmarks, and synchronization-aware evaluation models for generated audio--visual outputs. To address these limitations, we conduct a comprehensive study spanning data, benchmarking, and reward modeling. We first introduce SyncReward-Data-80K, a dataset containing 80K professional synchronization ratings for clips from eight audio--visual generators. A taxonomy-guided construction pipeline covers four sound-event families: Speech, Onset, Instrument, and Ambient. We further construct \textbf{SyncReward-Bench}, a held-out benchmark of 1K clips, each independently rated by multiple professionals. Using this benchmark, we systematically evaluate specialized synchronization metrics and omni-modal models, revealing their substantial misalignment with human judgments. Finally, we develop SyncReward, a reward model that combines semantic--temporal contrastive pretraining on real clips with human supervision on generated clips. As an evaluation metric, SyncReward achieves the strongest agreement with human ratings among the evaluated methods. As a reward, it improves synchronization through inference-time best-of-$N$ selection and reinforcement learning based post-training. We will release the data, benchmark, model, and code at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16338
PDF
-
What Matters in Preference Post-Training of Continuous Autoregressive Speech Language Models
2026-10-12 06:56:11Yingda Shen, Yao Qian, Dekun Chen, Yufei Liu, Junan Zhang, Chong Jing, Han Wang, Yuxiang Wang, Zhizheng WuAbstract
Continuous autoregressive speech language models combine an autoregressive (AR) backbone with a diffusion or flow-matching head. Preference post-training requires choosing how to construct pairs and which modules to update. Controlled interventions show that a perturbed acoustic patch changes subsequent backbone states, yet larger representation changes do not necessarily reduce speech quality. We construct preference pairs through noise or inference-configuration perturbations and formulate a preference update based on reference-relative flow-matching errors. Updating the backbone with a fixed head yields stronger reward improvements than head-only adaptation in our evaluated setting. Across flow-time and module ablations, the lowest training loss does not consistently produce the best speech. These findings support preference post-training that considers both acoustic sampling and autoregressive conditioning, with training choices validated on generated utterances.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16276
PDF
-
ScreenASR-Bench: A Tiered Benchmark for Speech Recognition with Visual Context
2026-10-12 06:36:20Mingwei Fu, Zheshu Song, Zhikai Zhou, Shen Huang, Shidong Shang, Mengxiao ZhuAbstract
Current ASR models perform well on general benchmarks but still struggle with acoustically ambiguous words. Visual context can aid recognition in screen-based scenarios, yet existing benchmarks provide limited insight into the benefits of different types of visual evidence. To address this gap, we introduce ScreenASR-Bench , a tiered benchmark with three progressively challenging levels: Explicit Textual Evidence (ETE), based on direct on-screen text; Explicit Visual Evidence (EVE), using visible content rather than on-screen text; and Implicit Semantic Evidence (ISE), requiring scene-level inference. Extensive experiments on ASR models, Large Audio-Language Models (LALMs) and Omni models show that incorporating visual context substantially improves recall over the audio-only setting across all three model families. The gains are largest for ETE and smallest for ISE, indicating that models leverage direct visual evidence more effectively than indirect semantic cues. To facilitate future research on visually grounded speech recognition, we publicly release ScreenASR-Bench.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16260
PDF
-
FOAdapter: A Plug-and-Play Spatial Tokenizer for Low-Bitrate FOA Speech Coding
2026-10-12 05:31:52Kirak Kim, Yoonjeong Park, Juhan Nam, Sungyoung Kim, Minje KimAbstract
Spatially encoded speech conveys not only linguistic information but also spatial cues. This enables listeners to distinguish and localize speakers, contributing to more natural and realistic auditory experiences in applications such as remote conferencing and immersive media. Neural speech codecs (NSCs) enable high-quality reconstruction of monaural speech at increasingly low bitrates while preserving linguistic information, but their ability to effectively preserve spatial cues remains limited. We propose FOAdapter, a plug-and-play spatial tokenizer that leverages a pretrained monaural speech codec to efficiently represent both linguistic and spatial information in first-order ambisonic (FOA) speech at low bitrates. Comprehensive evaluation demonstrates that FOAdapter consistently preserves spatial information across all evaluated codecs. Source code and audio examples are available on our demo website.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16202
PDF
-
The NVVSpeech Challenge 2026: Overview and Lessons for Speech Understanding and Generation with Nonverbal Vocalizations
2026-10-12 02:33:16Liumeng Xue, Yuang Cao, Jingbin Hu, Qirui Zhan, Huakang Chen, Yibin Zheng, Yunxiang Chen, Houdun Liu, Su Feng, Haibin Wu, Zheng Lian, Wei Xue, Bengu Wu, Hui Bu, Lei XieAbstract
Nonverbal vocalizations (NVVs), such as laughter and sighs, convey meaning alongside words. NVV-aware speech systems must recognize and generate these events while preserving lexical accuracy and perceptual quality. Yet differences in annotation, resources, and evaluation complicate comparisons, and aggregate scores can obscure specific weaknesses. We review ten system descriptions from the NVVSpeech Challenge 2026, covering understanding and generation in Chinese and English across 16 event categories. Our analysis examines supervision construction, task adaptation, and inference-time or preference-based feedback. Results reveal persistent recognition difficulties with breath and gasp and trade-offs between event recognition and lexical accuracy, as well as between generation intelligibility and acoustic quality, with human listening providing complementary evaluation evidence. These findings identify priorities for advancing NVV-aware speech understanding, controllable generation, and comparable evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16076
PDF
-
FlowGRPO for Vocal Separation: From Reward Analysis to Reward Design
2026-10-11 17:07:06Lishi Zuo, Chong-Xin Gan, Zezhong Jin, Youzhi Tu, Man-Wai Mak, KongAik LeeAbstract
The Flow Matching objective supervises the velocity field at intermediate states, whereas waveform metrics are evaluated after decoding and may be non-differentiable. To align Flow Matching models with waveform-level and perceptual quality objectives during post-training, FlowGRPO optimizes their trajectories using endpoint rewards. In this work, we focus on music separation and use multi-resolution short-time Fourier transform (MRSTFT), scale-invariant signal-to-distortion ratio (SI-SDR), and Virtual Speech Quality Objective Listener (ViSQOL) as reward components. Before policy optimization, we analyze the relationship between data quality factors and the within-group gap between the maximum and mean rollout rewards for each component. This analysis motivates a revised ViSQOL reward that matches channel-wise root-mean-square (RMS) levels and evaluates the interval from the first to the last active frame, retaining inactive frames within that interval. We also apply a sample-quality filter based on predefined waveform checks. Together, the revised reward and quality filter enable FlowGRPO to improve the pretrained vocal separator in both separation performance and perceptual quality.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15780
PDF
-
Synthesizing Ultrasonic Echo Profiles from Text for Open-Vocabulary Silent Speech Recognition
2026-10-11 14:49:19Jiacheng Liu, Ruidong Zhang, Fran\c{c}ois Guimbreti\`ere, Cheng ZhangAbstract
Eyewear that senses articulation with inaudible ultrasound can now recognize silent speech over an open vocabulary, but its accuracy is limited by the cost of training data. We present SoniGAN, which synthesizes the ultrasonic echo profiles of silent articulation from text and uses them as synthetic supervision. A voice-cloned text-to-speech (TTS) model reads a text corpus, and a two-stage generator synthesizes echo profiles from representations of the spoken content of that audio. Pretraining a recognizer on 104 hours of the synthesized data improves the word error rate (WER) of a public open-vocabulary benchmark by 2.3 points. Adding the sessions the corpus discards for a faulty microphone brings the system to 22.2% without any language model. Lexicon-constrained decoding, LLM rescoring, and ensembling further bring it to 14.9%, the first minimally obtrusive silent speech interface to fall inside the error range in which users report no loss of willingness to use silent speech input.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15671
PDF
-
AnyEdit: A Unified Framework for Speech and Singing Voice Editing with Real-World Environmental Consistency
2026-10-11 14:45:42Yunjia Zhang, Junan Zhang, Jing Yang, Xueyao Zhang, Fan Fan, Zhizheng WuAbstract
We present AnyEdit, a unified, separation-free framework for speech and singing voice editing that preserves real-world acoustic environments, including noise, reverberation, and background music. Recent unified generative models already achieve strong speech and singing generation in clean conditions, but real-world vocal editing remains challenging because the model must revise content while simultaneously preserving speaker identity, prosody, and the surrounding acoustic scene. Directly modeling noisy audio end-to-end entangles semantic editing with environmental acoustics, weakening the core vocal generation capability. We therefore adopt a two-stage design that preserves clean-domain editing ability while deferring acoustic rendering to a separate stage: an instruction-guided autoregressive editor first predicts clean prosody and content-style tokens, supported by a teacher-student noise-robust prosody tokenizer that distills clean prosodic tokens from degraded recordings; a flow-matching acoustic model then performs in-context rendering conditioned on the source acoustic context, so the edited segment inherits surrounding noise, reverberation, and background sound while maintaining consistent speaker timbre. To stabilize unedited regions, we introduce unmodified-area-aware supervision; after pre-training, we further apply direct preference optimization on mined real-to-real singing pairs. We also release AnyEditBench, a benchmark covering both speech and singing voice editing under clean, simulated, and in-the-wild acoustic conditions. Experiments on Chinese and English speech and singing datasets showed that AnyEdit consistently outperforms strong baselines in content accuracy, subjective quality, and background consistency under noisy and reverberant conditions. Demo: this https URL. AnyEditBench: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15665
PDF
-
BridgeCodec: Mamba Enhanced Neural Audio Codec with Schr'odinger Bridge at Low Bitrate
2026-10-11 08:54:53Zijian Lin, Jing Yang, Jinghao Luo, Zhuo Wang, Fan Fan, Zhiyong WuAbstract
Neural audio codecs achieve remarkable performance but operate as closed ecosystems with rigidly co-trained encoderdecoder pairs, severely hindering interoperability. To resolve this, we propose BridgeCodec, a versatile framework that decouples these pairs by translating latent representations between mismatched, frozen endpoints. We formulate this cross-codec translation as a Schrödinger Bridge optimal transport problem, enabling robust mapping between disparate distributions without predefined noise priors. To efficiently capture longrange speech temporal dependencies, we integrate a Mambaenhanced U-Net architecture. We validate BridgeCodec on an extreme deployment scenario: mapping a lightweight 8 kHz source encoder directly to a 48 kHz target decoder at an ultralow bitrate of 1 kbps. Experimental results demonstrate that BridgeCodec achieves superior wideband reconstruction and high perceptual quality, successfully bridging heavily bottlenecked, heterogeneous codecs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15453
PDF
-
Learning from Real Stuttering: Synthetic Mandarin Stuttering Speech for Data Augmentation in Speech Recognition
2026-10-11 07:18:30Yao Lu, Jiaming Zhou, Zhongyuan Fu, Yong QinAbstract
Mandarin stuttered speech remains under-resourced, limiting the development of robust speech processing systems. We present a Mandarin stuttering speech synthesis and data augmentation framework that adapts both autoregressive and non-autoregressive TTS models using naturally stuttered speech. Specifically, we adapt CosyVoice2 and MaskGCT to support controllable generation of specific stuttering events while also modeling broader utterance-level characteristics of stuttered speech. Using the adapted models, we construct synthetic data resources for downstream augmentation. Evaluations show that the generated speech closely approaches real stuttered speech. Extensive ASR experiments demonstrate consistent augmentation gains and further observe a domain-gap--diversity trade-off between synthetic and real data. These results demonstrate the value of learning synthetic stuttering data directly from real dysfluency for robust Mandarin speech processing.
Abstract (translated)
URL
https://arxiv.org/abs/2606.21457
PDF
-
The Impact of Side Information on Voice Privacy
2026-10-10 21:07:08Eulalie Thiombiano, Martha Larson, Vincent Colotte, Emmanuel VincentAbstract
Currently, voice-related privacy risks are studied under the assumption that the attacker has access only to spoken audio. In contrast, real-world collections often pair the speech signal with side information; yet to our knowledge, no publicly available dataset provides sufficiently detailed and directly linkable speech and side-information pairs to evaluate the combined risk. We propose a distribution-constrained method to build a semi-synthetic dataset and study singling out risk when geographic side information is assumed to accompany anonymized speech. We instantiate it using the English portion of Mozilla Common Voice and the 2021 UK Census, under ignorant and semi-informed attackers, and introduce a conditional reference that isolates the contribution of the audio beyond the candidate-set reduction induced by the side information. In our controlled geographic case study, for single-utterance speakers, the semi-informed attacker reaches an observed isolation probability of 0.718 in the finest OA-plus-household setting, compared with 0.380 in the signal-only setting; its excess over the conditional reference increases from 0.012 to 0.340. The ignorant attacker shows the same trend at a lower level. The effect is largest at fine granularity and short recordings, precisely the setting in which signal-only evaluation looks safest. Our results show that geographic side information can increase the singling out risk of anonymized speech, and we recommend including attacker settings with side information in future studies of voice privacy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.26884
PDF
-
Word-Aligned Prosody Reflects Speaker Differences More Than Depression or PTSD Severity
2026-10-10 21:01:51Hsiang-Chen Yeh, Aurosweta Mahapatra, Shreeram Suresh Chandra, Ryan L. Boyd, Berrak SismanAbstract
Word-aligned prosody is increasingly used to detect depression and posttraumatic stress disorder (PTSD), yet the stability and clinical relevance of these measurements remain unclear. We examine stability at two levels. At the word level, we ask whether a speaker produces the same word in a similar speaker-specific way across different utterance contexts. At the speaker level, we ask whether averaging prosody across many words produces consistent speaker scores across separate recordings. Drawing on principles of psychological measurement, we compare these representations in four corpora spanning acted, spontaneous, and clinical speech. Word-specific deviations show little cross-context recurrence (0.01-0.16), whereas speaker summaries are highly consistent, reaching 0.997 in ESD, 0.73-0.90 in MSP-Podcast, and 0.84-0.996 in DAIC-WOZ and PTSD-STOP. Despite this consistency, associations with depression or PTSD severity do not exceed 0.15; equivalence tests exclude effects of 0.30 in all analyses and 0.20 in DAIC-WOZ, while within-person associations with daily PTSD symptoms are near zero ($|\rho|\leq0.04$). Thus, aggregation yields stable speaker-level prosodic measures, but these measures do not detectably track depression or PTSD severity in the studied corpora. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15181
PDF
-
GAMW: Generation-Aware Mel-Domain Watermarking for TTS Traceability
2026-10-10 17:30:02Yihang Zhang, Weicai Yan, Qifei Zhang, Yangyang Wu, Tao JinAbstract
As text-to-speech (TTS) systems continue to advance, provenance tracking and security verification of synthesized speech have become increasingly important. Audio watermarking provides active provenance by embedding imperceptible, machine-recoverable information into speech. However, existing post-hoc methods typically modify the waveform after synthesis, leaving the watermark vulnerable to compound perturbations. To address this limitation, we propose GAMW, a watermark injection framework integrated into the TTS generation process. Before waveform synthesis, GAMW embeds a content-adaptive multi-bit watermark residual into the generated representation, and its decoding objective combines focal modulation with dynamic per-bit weighting. We train and evaluate GAMW separately on two TTS backbones. With a 16-bit payload, GAMW improves decoding accuracy over the strongest baseline by 9.2 and 23.5 percentage points under individual and compound perturbations, respectively, while maintaining competitive speech quality. Reliable clean-speech decoding is also retained at higher payloads. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15082
PDF
-
How Language-Independent Are Emotional Attributes? A Study on Training Data Scaling and Cross-Lingual Generalization
Abstract
Current state-of-the-art Speech Emotion Recognition (SER) systems rely on lots of training data, which is available only for a few languages such as English. For low-resource languages, using a cross-lingual model or adapting it to the target language might be an alternative to training a mono-lingual model from scratch. However, it is not clear what constitutes a "low-resource", i.e. where model adaptation loses its edge over the mono-lingual approach. We investigate this topic by training and adapting several SER models on English and Mandarin data, focusing on the emotional attributes of arousal, valence and dominance. Our results show that, for arousal, model adaptation is beneficial even with two hours of data, while for valence 10-20 hours of adaptation material is required to match the performance of a mono-lingual model trained with 100 hours of data. This indicates that task-specific model adaptation may be an effective approach in low-resource speech emotion recognition problems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15059
PDF
