53 citations · 205 across the 57 of their papers we have counts for
57 papers
The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties
William Chen, Chutong Meng, Jiatong Shi +10
Recent improvements in multilingual ASR have not been equally distributed across languages and language varieties. To advance state-of-the-art (SOTA) ASR models, we present the Int…
Improving Speech Enhancement with Multi-Metric Supervision from Learned Quality Assessment
Wei Wang, Wangyou Zhang, Chenda Li +3
Speech quality assessment (SQA) aims to predict the perceived quality of speech signals under a wide range of distortions. It is inherently connected to speech enhancement (SE), wh…
Discrete Audio Tokens: More Than a Survey!
Pooneh Mousavi, Gallil Maimon, Adel Moumen +18
Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics while enabling efficient storage and infere…
Uni-VERSA: Versatile Speech Assessment with a Unified Network
Jiatong Shi, Hye-Jin Shim, Shinji Watanabe
Subjective listening tests remain the golden standard for speech quality assessment, but are costly, variable, and difficult to scale. In contrast, existing objective metrics, such…
Aligning Text-to-Music Evaluation with Human Preferences
Yichen Huang, Zachary Novack, Koichi Saito +5
Despite significant recent advances in generative acoustic text-to-music (TTM) modeling, robust evaluation of these models lags behind, relying in particular on the popular Fréchet…
Fusion of Discrete Representations and Self-Augmented Representations for Multilingual Automatic Speech Recognition
Shih-heng Wang, Jiatong Shi, Chien-yu Huang +2
Self-supervised learning (SSL) models have shown exceptional capabilities across various speech-processing tasks. Continuous SSL representations are effective but suffer from high…
Findings of the IWSLT 2024 Evaluation Campaign
Ibrahim Said Ahmad, Antonios Anastasopoulos, Ondřej Bojar +42
This paper reports on the shared tasks organized by the 21st IWSLT Conference. The shared tasks address 7 scientific challenges in spoken language translation: simultaneous and off…
How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenario
Shih-Heng Wang, Zih-Ching Chen, Jiatong Shi +6
The utilization of speech Self-Supervised Learning (SSL) models achieves impressive performance on Automatic Speech Recognition (ASR). However, in low-resource language ASR, they e…
ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration
Masao Someki, Kwanghee Choi, Siddhant Arora +7
We introduce ESPnet-EZ, an extension of the open-source speech processing toolkit ESPnet, aimed at quick and easy development of speech models. ESPnet-EZ focuses on two major aspec…
Towards Robust Speech Representation Learning for Thousands of Languages
William Chen, Wangyou Zhang, Yifan Peng +7
Self-supervised learning (SSL) has helped extend speech technologies to more languages by reducing the need for labeled data. However, models are still far from supporting the worl…
MMM: Multi-Layer Multi-Residual Multi-Stream Discrete Speech Representation from Self-supervised Learning Model
Jiatong Shi, Xutai Ma, Hirofumi Inaguma +2
Speech discrete representation has proven effective in various downstream applications due to its superior compression rate of the waveform, fast convergence during training, and c…
ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets
Jiatong Shi, Shih-Heng Wang, William Chen +8
ML-SUPERB evaluates self-supervised learning (SSL) models on the tasks of language identification and automatic speech recognition (ASR). This benchmark treats the models as featur…
Joint Beam Search Integrating CTC, Attention, and Transducer Decoders
Yui Sudo, Muhammad Shakeel, Yosuke Fukumoto +4
End-to-end automatic speech recognition (E2E-ASR) can be classified by its decoder architectures, such as connectionist temporal classification (CTC), recurrent neural network tran…
A Large-Scale Evaluation of Speech Foundation Models
Shu-wen Yang, Heng-Jui Chang, Zili Huang +18
The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific modeling a…
Wav2Gloss: Generating Interlinear Glossed Text from Speech
Taiqi He, Kwanghee Choi, Lindia Tjuatja +6
Thousands of the world's languages are in danger of extinction--a tremendous threat to cultural identities and human language diversity. Interlinear Glossed Text (IGT) is a form of…
Singing Voice Data Scaling-up: An Introduction to ACE-Opencpop and ACE-KiSing
Jiatong Shi, Yueqian Lin, Xinyi Bai +6
In singing voice synthesis (SVS), generating singing voices from musical scores faces challenges due to limited data availability. This study proposes a unique strategy to address…
ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models
Jee-weon Jung, Wangyou Zhang, Jiatong Shi +5
This paper introduces ESPnet-SPK, a toolkit designed with several objectives for training speaker embedding extractors. First, we provide an open-source platform for researchers in…
OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer
Yifan Peng, Jinchuan Tian, William Chen +9
Recent studies have highlighted the importance of fully open foundation models. The Open Whisper-style Speech Model (OWSM) is an initial step towards reproducing OpenAI Whisper usi…
Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data
Yifan Peng, Jinchuan Tian, Brian Yan +13
Pre-training speech models on large volumes of data has achieved remarkable success. OpenAI Whisper is a multilingual multitask model trained on 680k hours of supervised speech dat…
HuBERTopic: Enhancing Semantic Representation of HuBERT through Self-supervision Utilizing Topic Model
Takashi Maekaku, Jiatong Shi, Xuankai Chang +2
Recently, the usefulness of self-supervised representation learning (SSRL) methods has been confirmed in various downstream tasks. Many of these models, as exemplified by HuBERT an…
Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyond
Jiatong Shi, William Chen, Dan Berrebbi +10
The 2023 Multilingual Speech Universal Performance Benchmark (ML-SUPERB) Challenge expands upon the acclaimed SUPERB framework, emphasizing self-supervised models in multilingual s…
EFFUSE: Efficient Self-Supervised Feature Fusion for E2E ASR in Low Resource and Multilingual Scenarios
Tejes Srivastava, Jiatong Shi, William Chen +1
Self-Supervised Learning (SSL) models have demonstrated exceptional performance in various speech tasks, particularly in low-resource and multilingual domains. Recent works show th…
Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction
Jiatong Shi, Hirofumi Inaguma, Xutai Ma +2
Existing Self-Supervised Learning (SSL) models for speech typically process speech signals at a fixed resolution of 20 milliseconds. This approach overlooks the varying information…
UniAudio: An Audio Foundation Model Toward Universal Audio Generation
Dongchao Yang, Jinchuan Tian, Xu Tan +9
Large Language models (LLM) have demonstrated the capability to handle a variety of generative tasks. This paper presents the UniAudio system, which, unlike prior task-specific app…