Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization

Low latency speech human-machine communication is becoming increasingly necessary as speech technology advances quickly in the last decade. One of the primary factors behind the advancement of speech technology is self-supervised learning. Most self-supervised learning algorithms are designed with full utterance assumption and compromises have to made if partial utterances are presented, which are common in the streaming applications. In this work, we propose a chunk based self-supervised learning (Chunk SSL) algorithm as an unified solution for both streaming and offline speech pre-training. Chunk SSL is optimized with the masked prediction loss and an acoustic encoder is encouraged to restore indices of those masked speech frames with help from unmasked frames in the same chunk and preceding chunks. A copy and append data augmentation approach is proposed to conduct efficient chunk based pre-training. Chunk SSL utilizes a finite scalar quantization (FSQ) module to discretize input speech features and our study shows a high resolution FSQ codebook, i.e., a codebook with vocabulary size up to a few millions, is beneficial to transfer knowledge from the pre-training task to the downstream tasks. A group masked prediction loss is employed during pre-training to alleviate the high memory and computation cost introduced by the large codebook. The proposed approach is examined in two speech to text tasks, i.e., speech recognition and speech translation. Experimental results on the \textsc{Librispeech} and \textsc{Must-C} datasets show that the proposed method could achieve very competitive results for speech to text tasks at both streaming and offline modes.

Impact of Phonetics on Speaker Identity in Adversarial Voice Attack

Adversarial perturbations in speech pose a serious threat to automatic speech recognition (ASR) and speaker verification by introducing subtle waveform modifications that remain imperceptible to humans but can significantly alter system outputs. While targeted attacks on end-to-end ASR models have been widely studied, the phonetic basis of these perturbations and their effect on speaker identity remain underexplored. In this work, we analyze adversarial audio at the phonetic level and show that perturbations exploit systematic confusions such as vowel centralization and consonant substitutions. These distortions not only mislead transcription but also degrade phonetic cues critical for speaker verification, leading to identity drift. Using DeepSpeech as our ASR target, we generate targeted adversarial examples and evaluate their impact on speaker embeddings across genuine and impostor samples. Results across 16 phonetically diverse target phrases demonstrate that adversarial audio induces both transcription errors and identity drift, highlighting the need for phonetic-aware defenses to ensure the robustness of ASR and speaker recognition systems.

From Who Said What to Who They Are: Modular Training-free Identity-Aware LLM Refinement of Speaker Diarization

Speaker diarization (SD) struggles in real-world scenarios due to dynamic environments and unknown speaker counts. SD is rarely used alone and is often paired with automatic speech recognition (ASR), but non-modular methods that jointly train on domain-specific data have limited flexibility. Moreover, many applications require true speaker identities rather than SD's pseudo labels. We propose a training-free modular pipeline combining off-the-shelf SD, ASR, and a large language model (LLM) to determine who spoke, what was said, and who they are. Using structured LLM prompting on reconciled SD and ASR outputs, our method leverages semantic continuity in conversational context to refine low-confidence speaker labels and assigns role identities while correcting split speakers. On a real-world patient-clinician dataset, our approach achieves a 29.7% relative error reduction over baseline reconciled SD and ASR. It enhances diarization performance without additional training and delivers a complete pipeline for SD, ASR, and speaker identity detection in practical applications.

Few-shot Personalization via In-Context Learning for Speech Emotion Recognition based on Speech-Language Model

This paper proposes a personalization method for speech emotion recognition (SER) through in-context learning (ICL). Since the expression of emotions varies from person to person, speaker-specific adaptation is crucial for improving the SER performance. Conventional SER methods have been personalized using emotional utterances of a target speaker, but it is often difficult to prepare utterances corresponding to all emotion labels in advance. Our idea to overcome this difficulty is to obtain speaker characteristics by conditioning a few emotional utterances of the target speaker in ICL-based inference. ICL is a method to perform unseen tasks by conditioning a few input-output examples through inference in large language models (LLMs). We meta-train a speech-language model extended from the LLM to learn how to perform personalized SER via ICL. Experimental results using our newly collected SER dataset demonstrate that the proposed method outperforms conventional methods.

Language Conditioning Improves Accuracy of Aircraft Goal Prediction in Untowered Airspace

Autonomous aircraft must safely operate in untowered airspace, where coordination relies on voice-based communication among human pilots. Safe operation requires an aircraft to predict the intent, and corresponding goal location, of other aircraft. This paper introduces a multimodal framework for aircraft goal prediction that integrates natural language understanding with spatial reasoning to improve autonomous decision-making in such environments. We leverage automatic speech recognition and large language models to transcribe and interpret pilot radio calls, identify aircraft, and extract discrete intent labels. These intent labels are fused with observed trajectories to condition a temporal convolutional network and Gaussian mixture model for probabilistic goal prediction. Our method significantly reduces goal prediction error compared to baselines that rely solely on motion history, demonstrating that language-conditioned prediction increases prediction accuracy. Experiments on a real-world dataset from an untowered airport validate the approach and highlight its potential to enable socially aware, language-conditioned robotic motion planning.

Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST

This report introduces Canary-1B-v2, a fast, robust multilingual model for Automatic Speech Recognition (ASR) and Speech-to-Text Translation (AST). Built with a FastConformer encoder and Transformer decoder, it supports 25 languages primarily European. The model was trained on 1.7M hours of total data samples, including Granary and NeMo ASR Set 3.0, with non-speech audio added to reduce hallucinations for ASR and AST. We describe its two-stage pre-training and fine-tuning process with dynamic data balancing, as well as experiments with an nGPT encoder. Results show nGPT scales well with massive data, while FastConformer excels after fine-tuning. For timestamps, Canary-1B-v2 uses the NeMo Forced Aligner (NFA) with an auxiliary CTC model, providing reliable segment-level timestamps for ASR and AST. Evaluations show Canary-1B-v2 outperforms Whisper-large-v3 on English ASR while being 10x faster, and delivers competitive multilingual ASR and AST performance against larger models like Seamless-M4T-v2-large and LLM-based systems. We also release Parakeet-TDT-0.6B-v3, a successor to v2, offering multilingual ASR across the same 25 languages with just 600M parameters.

Behind the Scenes: Mechanistic Interpretability of LoRA-adapted Whisper for Speech Emotion Recognition

Large pre-trained speech models such as Whisper offer strong generalization but pose significant challenges for resource-efficient adaptation. Low-Rank Adaptation (LoRA) has become a popular parameter-efficient fine-tuning method, yet its underlying mechanisms in speech tasks remain poorly understood. In this work, we conduct the first systematic mechanistic interpretability study of LoRA within the Whisper encoder for speech emotion recognition (SER). Using a suite of analytical tools, including layer contribution probing, logit-lens inspection, and representational similarity via singular value decomposition (SVD) and centered kernel alignment (CKA), we reveal two key mechanisms: a delayed specialization process that preserves general features in early layers before consolidating task-specific information, and a forward alignment, backward differentiation dynamic between LoRA's matrices. Our findings clarify how LoRA reshapes encoder hierarchies, providing both empirical insights and a deeper mechanistic understanding for designing efficient and interpretable adaptation strategies in large speech models. Our code is available at https://github.com/harryporry77/Behind-the-Scenes.

CS-FLEURS: A Massively Multilingual and Code-Switched Speech Dataset

We present CS-FLEURS, a new dataset for developing and evaluating code-switched speech recognition and translation systems beyond high-resourced languages. CS-FLEURS consists of 4 test sets which cover in total 113 unique code-switched language pairs across 52 languages: 1) a 14 X-English language pair set with real voices reading synthetically generated code-switched sentences, 2) a 16 X-English language pair set with generative text-to-speech 3) a 60 {Arabic, Mandarin, Hindi, Spanish}-X language pair set with the generative text-to-speech, and 4) a 45 X-English lower-resourced language pair test set with concatenative text-to-speech. Besides the four test sets, CS-FLEURS also provides a training set with 128 hours of generative text-to-speech data across 16 X-English language pairs. Our hope is that CS-FLEURS helps to broaden the scope of future code-switched speech research. Dataset link: https://huggingface.co/datasets/byan/cs-fleurs.

Joint Learning using Mixture-of-Expert-Based Representation for Enhanced Speech Generation and Robust Emotion Recognition

Speech emotion recognition (SER) plays a critical role in building emotion-aware speech systems, but its performance degrades significantly under noisy conditions. Although speech enhancement (SE) can improve robustness, it often introduces artifacts that obscure emotional cues and adds computational overhead to the pipeline. Multi-task learning (MTL) offers an alternative by jointly optimizing SE and SER tasks. However, conventional shared-backbone models frequently suffer from gradient interference and representational conflicts between tasks. To address these challenges, we propose the Sparse Mixture-of-Experts Representation Integration Technique (Sparse MERIT), a flexible MTL framework that applies frame-wise expert routing over self-supervised speech representations. Sparse MERIT incorporates task-specific gating networks that dynamically select from a shared pool of experts for each frame, enabling parameter-efficient and task-adaptive representation learning. Experiments on the MSP-Podcast corpus show that Sparse MERIT consistently outperforms baseline models on both SER and SE tasks. Under the most challenging condition of -5 dB signal-to-noise ratio (SNR), Sparse MERIT improves SER F1-macro by an average of 12.0% over a baseline relying on a SE pre-processing strategy, and by 3.4% over a naive MTL baseline, with statistical significance on unseen noise conditions. For SE, Sparse MERIT improves segmental SNR (SSNR) by 28.2% over the SE pre-processing baseline and by 20.0% over the naive MTL baseline. These results demonstrate that Sparse MERIT provides robust and generalizable performance for both emotion recognition and enhancement tasks in noisy environments.

Towards Improved Speech Recognition through Optimized Synthetic Data Generation

Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using a state-of-the-art text-to-speech model with voice cloning capabilities. Our goal is to achieve automatic speech recognition (ASR) performance comparable to models trained on real data. We explore ways to optimize synthetic data generation through finetuning, filtering and evaluation, and its use for training an end-to-end encoder-decoder ASR model. Experiments were conducted using two datasets of spontaneous, conversational speech in Qu\'ebec French. We show that improving data generation leads to large improvements in the final ASR system trained on synthetic data.