Copertina

Context-Driven Dynamic Pruning for Large Speech Foundation Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Someki, Masao, Bharadwaj, Shikhar, Joshi, Atharva Anand, Lin, Chyi-Jiunn, Tian, Jinchuan, Jung, Jee-weon, Müller, Markus, Susanj, Nathan, Liu, Jing, Watanabe, Shinji
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Audio and Speech Processing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

On-device Streaming Discrete Speech Units
di: Choi, Kwanghee, et al.
Pubblicazione: (2025)

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

Segment-Level Vectorized Beam Search Based on Partially Autoregressive Inference
di: Someki, Masao, et al.
Pubblicazione: (2023)

Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement
di: Zhang, Wangyou, et al.
Pubblicazione: (2024)

DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognition
di: Sudo, Yui, et al.
Pubblicazione: (2025)

Chain-of-Thought Training for Open E2E Spoken Dialogue Systems
di: Arora, Siddhant, et al.
Pubblicazione: (2025)

POWSM: A Phonetic Open Whisper-Style Speech Foundation Model
di: Li, Chin-Jou, et al.
Pubblicazione: (2025)

OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer
di: Peng, Yifan, et al.
Pubblicazione: (2024)

Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder
di: Shakeel, Muhammad, et al.
Pubblicazione: (2025)

CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR
di: Shakeel, Muhammad, et al.
Pubblicazione: (2026)

Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing
di: Shim, Hye-jin, et al.
Pubblicazione: (2024)

Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?
di: Aldeneh, Zakaria, et al.
Pubblicazione: (2024)

Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks
di: Maiti, Soumi, et al.
Pubblicazione: (2023)

On the Evaluation of Speech Foundation Models for Spoken Language Understanding
di: Arora, Siddhant, et al.
Pubblicazione: (2024)

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

Text-To-Speech Synthesis In The Wild
di: Jung, Jee-weon, et al.
Pubblicazione: (2024)

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

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

Balancing Speech Understanding and Generation Using Continual Pre-training for Codec-based Speech LLM
di: Shi, Jiatong, et al.
Pubblicazione: (2025)

OpusLM: A Family of Open Unified Speech Language Models
di: Tian, Jinchuan, et al.
Pubblicazione: (2025)

SpoofCeleb: Speech Deepfake Detection and SASV In The Wild
di: Jung, Jee-weon, et al.
Pubblicazione: (2024)

Reasoning Beyond Majority Vote: An Explainable SpeechLM Framework for Speech Emotion Recognition
di: Su, Bo-Hao, et al.
Pubblicazione: (2025)

OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder
di: Bharadwaj, Shikhar, et al.
Pubblicazione: (2025)

The CMU-AIST submission for the ICME 2025 Audio Encoder Challenge
di: Bharadwaj, Shikhar, et al.
Pubblicazione: (2026)

PURE Codec: Progressive Unfolding of Residual Entropy for Speech Codec Learning
di: Shi, Jiatong, et al.
Pubblicazione: (2025)

ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and Speech
di: Shi, Jiatong, et al.
Pubblicazione: (2024)

Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels
di: Aldeneh, Zakaria, et al.
Pubblicazione: (2024)

ESPnet-SpeechLM: An Open Speech Language Model Toolkit
di: Tian, Jinchuan, et al.
Pubblicazione: (2025)

Disentangled Representation Learning for Environment-agnostic Speaker Recognition
di: Nam, KiHyun, et al.
Pubblicazione: (2024)

Do Neural Codecs Generalize? A Controlled Study Across Unseen Languages and Non-Speech Tasks
di: Wang, Shih-Heng, et al.
Pubblicazione: (2026)

ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models
di: Jung, Jee-weon, et al.
Pubblicazione: (2024)

UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions
di: Arora, Siddhant, et al.
Pubblicazione: (2023)

To what extent can ASV systems naturally defend against spoofing attacks?
di: Jung, Jee-weon, et al.
Pubblicazione: (2024)

BSCodec: A Band-Split Neural Codec for High-Quality Universal Audio Reconstruction
di: Wang, Haoran, et al.
Pubblicazione: (2025)

Token-based Attractors and Cross-attention in Spoof Diarization
di: Koo, Kyo-Won, et al.
Pubblicazione: (2025)

TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages
di: Kim, Minsu, et al.
Pubblicazione: (2024)

ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems
di: Arora, Siddhant, et al.
Pubblicazione: (2025)

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

STAB: Speech Tokenizer Assessment Benchmark
di: Vashishth, Shikhar, et al.
Pubblicazione: (2024)