Cover Image

Improving Multilingual Speech Models on ML-SUPERB 2.0: Fine-tuning with Data Augmentation and LID-Aware CTC

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Qingzheng, Sun, Jiancheng, Peng, Yifan, Watanabe, Shinji
Format:	Preprint
Published:	2025
Subjects:	Sound Computation and Language Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ML-SUPERB: Multilingual Speech Universal PERformance Benchmark
by: Shi, Jiatong, et al.
Published: (2023)

ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets
by: Shi, Jiatong, et al.
Published: (2024)

Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation
by: Tsunoo, Emiru, et al.
Published: (2023)

OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification
by: Peng, Yifan, et al.
Published: (2024)

Fusion of Discrete Representations and Self-Augmented Representations for Multilingual Automatic Speech Recognition
by: Wang, Shih-heng, et al.
Published: (2024)

EMO-SUPERB: An In-depth Look at Speech Emotion Recognition
by: Wu, Haibin, et al.
Published: (2024)

Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech
by: Huang, Chien-yu, et al.
Published: (2023)

Joint Beam Search Integrating CTC, Attention, and Transducer Decoders
by: Sudo, Yui, et al.
Published: (2024)

Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyond
by: Shi, Jiatong, et al.
Published: (2023)

Improving Design of Input Condition Invariant Speech Enhancement
by: Zhang, Wangyou, et al.
Published: (2024)

CTC Blank Triggered Dynamic Layer-Skipping for Efficient CTC-based Speech Recognition
by: Hou, Junfeng, et al.
Published: (2024)

SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics
by: Saeki, Takaaki, et al.
Published: (2024)

USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models
by: Ding, Shaojin, et al.
Published: (2023)

Codec-SUPERB @ SLT 2024: A lightweight benchmark for neural audio codec models
by: Wu, Haibin, et al.
Published: (2024)

Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation
by: Wang, Huimeng, et al.
Published: (2024)

SegAug: CTC-Aligned Segmented Augmentation For Robust RNN-Transducer Based Speech Recognition
by: Le, Khanh, et al.
Published: (2025)

Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Loss
by: Shakeel, Muhammad, et al.
Published: (2024)

LID Models are Actually Accent Classifiers: Implications and Solutions for LID on Accented Speech
by: Bafna, Niyati, et al.
Published: (2025)

OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning
by: Peng, Yifan, et al.
Published: (2025)

On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models
by: Tian, Jinchuan, et al.
Published: (2024)

Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation
by: Wu, Shih-Lun, et al.
Published: (2023)

Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation
by: Shakeel, Muhammad, et al.
Published: (2024)

Improving Speech Enhancement with Multi-Metric Supervision from Learned Quality Assessment
by: Wang, Wei, et al.
Published: (2025)

Codec-SUPERB: An In-Depth Analysis of Sound Codec Models
by: Wu, Haibin, et al.
Published: (2024)

TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models
by: Peng, Junyi, et al.
Published: (2025)

ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration
by: Someki, Masao, et al.
Published: (2024)

Contextualized Automatic Speech Recognition with Dynamic Vocabulary
by: Sudo, Yui, et al.
Published: (2024)

Uni-VERSA: Versatile Speech Assessment with a Unified Network
by: Shi, Jiatong, et al.
Published: (2025)

EFFUSE: Efficient Self-Supervised Feature Fusion for E2E ASR in Low Resource and Multilingual Scenarios
by: Srivastava, Tejes, et al.
Published: (2023)

Diffusion-based Generative Modeling with Discriminative Guidance for Streamable Speech Enhancement
by: Li, Chenda, et al.
Published: (2024)

MMM: Multi-Layer Multi-Residual Multi-Stream Discrete Speech Representation from Self-supervised Learning Model
by: Shi, Jiatong, et al.
Published: (2024)

Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search
by: Sudo, Yui, et al.
Published: (2024)

Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking
by: Yan, Brian, et al.
Published: (2024)

Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC
by: Kang, Jiawen, et al.
Published: (2024)

kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels
by: Zhou, Jiaming, et al.
Published: (2023)

Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition
by: Cornell, Samuele, et al.
Published: (2024)

S2ST-Omni: Hierarchical Language-Aware SpeechLLM Adaptation for Multilingual Speech-to-Speech Translation
by: Pan, Yu, et al.
Published: (2025)

Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting
by: Kashiwagi, Yosuke, et al.
Published: (2024)

Evaluating Self-Supervised Speech Models via Text-Based LLMS
by: Maekaku, Takashi, et al.
Published: (2025)

Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis
by: Liao, Shijia, et al.
Published: (2024)