Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling

We introduce Delayed Streams Modeling (DSM), a flexible formulation for streaming, multimodal sequence-to-sequence learning. Sequence-to-sequence generation is often cast in an offline manner, where the model consumes the complete input sequence before generating the first output timestep. Alternatively, streaming sequence-to-sequence rely on learning a policy for choosing when to advance on the input stream, or write to the output stream. DSM instead models already time-aligned streams with a decoder-only language model. By moving the alignment to a pre-processing step,and introducing appropriate delays between streams, DSM provides streaming inference of arbitrary output sequences, from any input combination, making it applicable to many sequence-to-sequence problems. In particular, given text and audio streams, automatic speech recognition (ASR) corresponds to the text stream being delayed, while the opposite gives a text-to-speech (TTS) model. We perform extensive experiments for these two major sequence-to-sequence tasks, showing that DSM provides state-of-the-art performance and latency while supporting arbitrary long sequences, being even competitive with offline baselines. Code, samples and demos are available at https://github.com/kyutai-labs/delayed-streams-modeling

A Bottom-up Framework with Language-universal Speech Attribute Modeling for Syllable-based ASR

We propose a bottom-up framework for automatic speech recognition (ASR) in syllable-based languages by unifying language-universal articulatory attribute modeling with syllable-level prediction. The system first recognizes sequences or lattices of articulatory attributes that serve as a language-universal, interpretable representation of pronunciation, and then transforms them into syllables through a structured knowledge integration process. We introduce two evaluation metrics, namely Pronunciation Error Rate (PrER) and Syllable Homonym Error Rate (SHER), to evaluate the model's ability to capture pronunciation and handle syllable ambiguities. Experimental results on the AISHELL-1 Mandarin corpus demonstrate that the proposed bottom-up framework achieves competitive performance and exhibits better robustness under low-resource conditions compared to the direct syllable prediction model. Furthermore, we investigate the zero-shot cross-lingual transferability on Japanese and demonstrate significant improvements over character- and phoneme-based baselines by 40% error rate reduction.

CAMÕES: A Comprehensive Automatic Speech Recognition Benchmark for European Portuguese

Existing resources for Automatic Speech Recognition in Portuguese are mostly focused on Brazilian Portuguese, leaving European Portuguese (EP) and other varieties under-explored. To bridge this gap, we introduce CAM\~OES, the first open framework for EP and other Portuguese varieties. It consists of (1) a comprehensive evaluation benchmark, including 46h of EP test data spanning multiple domains; and (2) a collection of state-of-the-art models. For the latter, we consider multiple foundation models, evaluating their zero-shot and fine-tuned performances, as well as E-Branchformer models trained from scratch. A curated set of 425h of EP was used for both fine-tuning and training. Our results show comparable performance for EP between fine-tuned foundation models and the E-Branchformer. Furthermore, the best-performing models achieve relative improvements above 35% WER, compared to the strongest zero-shot foundation model, establishing a new state-of-the-art for EP and other varieties.

A Study of the Removability of Speaker-Adversarial Perturbations

Recent advancements in adversarial attacks have demonstrated their effectiveness in misleading speaker recognition models, making wrong predictions about speaker identities. On the other hand, defense techniques against speaker-adversarial attacks focus on reducing the effects of speaker-adversarial perturbations on speaker attribute extraction. These techniques do not seek to fully remove the perturbations and restore the original speech. To this end, this paper studies the removability of speaker-adversarial perturbations. Specifically, the investigation is conducted assuming various degrees of awareness of the perturbation generator across three scenarios: ignorant, semi-informed, and well-informed. Besides, we consider both the optimization-based and feedforward perturbation generation methods. Experiments conducted on the LibriSpeech dataset demonstrated that: 1) in the ignorant scenario, speaker-adversarial perturbations cannot be eliminated, although their impact on speaker attribute extraction is reduced, 2) in the semi-informed scenario, the speaker-adversarial perturbations cannot be fully removed, while those generated by the feedforward model can be considerably reduced, and 3) in the well-informed scenario, speaker-adversarial perturbations are nearly eliminated, allowing for the restoration of the original speech. Audio samples can be found in https://voiceprivacy.github.io/Perturbation-Generation-Removal/.

LatPhon: Lightweight Multilingual G2P for Romance Languages and English

Grapheme-to-phoneme (G2P) conversion is a key front-end for text-to-speech (TTS), automatic speech recognition (ASR), speech-to-speech translation (S2ST) and alignment systems, especially across multiple Latin-script languages.We present LatPhon, a 7.5 M - parameter Transformer jointly trained on six such languages--English, Spanish, French, Italian, Portuguese, and Romanian. On the public ipa-dict corpus, it attains a mean phoneme error rate (PER) of 3.5%, outperforming the byte-level ByT5 baseline (5.4%) and approaching language-specific WFSTs (3.2%) while occupying 30 MB of memory, which makes on-device deployment feasible when needed. These results indicate that compact multilingual G2P can serve as a universal front-end for Latin-language speech pipelines.

Improving Noise Robust Audio-Visual Speech Recognition via Router-Gated Cross-Modal Feature Fusion

Robust audio-visual speech recognition (AVSR) in noisy environments remains challenging, as existing systems struggle to estimate audio reliability and dynamically adjust modality reliance. We propose router-gated cross-modal feature fusion, a novel AVSR framework that adaptively reweights audio and visual features based on token-level acoustic corruption scores. Using an audio-visual feature fusion-based router, our method down-weights unreliable audio tokens and reinforces visual cues through gated cross-attention in each decoder layer. This enables the model to pivot toward the visual modality when audio quality deteriorates. Experiments on LRS3 demonstrate that our approach achieves an 16.51-42.67% relative reduction in word error rate compared to AV-HuBERT. Ablation studies confirm that both the router and gating mechanism contribute to improved robustness under real-world acoustic noise.

Designing Practical Models for Isolated Word Visual Speech Recognition

Visual speech recognition (VSR) systems decode spoken words from an input sequence using only the video data. Practical applications of such systems include medical assistance as well as human-machine interactions. A VSR system is typically employed in a complementary role in cases where the audio is corrupt or not available. In order to accurately predict the spoken words, these architectures often rely on deep neural networks in order to extract meaningful representations from the input sequence. While deep architectures achieve impressive recognition performance, relying on such models incurs significant computation costs which translates into increased resource demands in terms of hardware requirements and results in limited applicability in real-world scenarios where resources might be constrained. This factor prevents wider adoption and deployment of speech recognition systems in more practical applications. In this work, we aim to alleviate this issue by developing architectures for VSR that have low hardware costs. Following the standard two-network design paradigm, where one network handles visual feature extraction and another one utilizes the extracted features to classify the entire sequence, we develop lightweight end-to-end architectures by first benchmarking efficient models from the image classification literature, and then adopting lightweight block designs in a temporal convolution network backbone. We create several unified models with low resource requirements but strong recognition performance. Experiments on the largest public database for English words demonstrate the effectiveness and practicality of our developed models. Code and trained models will be made publicly available.

Layer-wise Analysis for Quality of Multilingual Synthesized Speech

While supervised quality predictors for synthesized speech have demonstrated strong correlations with human ratings, their requirement for in-domain labeled training data hinders their generalization ability to new domains. Unsupervised approaches based on pretrained self-supervised learning (SSL) based models and automatic speech recognition (ASR) models are a promising alternative; however, little is known about how these models encode information about speech quality. Towards the goal of better understanding how different aspects of speech quality are encoded in a multilingual setting, we present a layer-wise analysis of multilingual pretrained speech models based on reference modeling. We find that features extracted from early SSL layers show correlations with human ratings of synthesized speech, and later layers of ASR models can predict quality of non-neural systems as well as intelligibility. We also demonstrate the importance of using well-matched reference data.

Contextualized Token Discrimination for Speech Search Query Correction

Query spelling correction is an important function of modern search engines since it effectively helps users express their intentions clearly. With the growing popularity of speech search driven by Automated Speech Recognition (ASR) systems, this paper introduces a novel method named Contextualized Token Discrimination (CTD) to conduct effective speech query correction. In CTD, we first employ BERT to generate token-level contextualized representations and then construct a composition layer to enhance semantic information. Finally, we produce the correct query according to the aggregated token representation, correcting the incorrect tokens by comparing the original token representations and the contextualized representations. Extensive experiments demonstrate the superior performance of our proposed method across all metrics, and we further present a new benchmark dataset with erroneous ASR transcriptions to offer comprehensive evaluations for audio query correction.

Speech Emotion Recognition via Entropy-Aware Score Selection

In this paper, we propose a multimodal framework for speech emotion recognition that leverages entropy-aware score selection to combine speech and textual predictions. The proposed method integrates a primary pipeline that consists of an acoustic model based on wav2vec2.0 and a secondary pipeline that consists of a sentiment analysis model using RoBERTa-XLM, with transcriptions generated via Whisper-large-v3. We propose a late score fusion approach based on entropy and varentropy thresholds to overcome the confidence constraints of primary pipeline predictions. A sentiment mapping strategy translates three sentiment categories into four target emotion classes, enabling coherent integration of multimodal predictions. The results on the IEMOCAP and MSP-IMPROV datasets show that the proposed method offers a practical and reliable enhancement over traditional single-modality systems.