Imagen de Portada

On-device Streaming Discrete Speech Units

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Choi, Kwanghee, Someki, Masao, Strubell, Emma, Watanabe, Shinji
Formato:	Preprint
Publicado:	2025
Materias:	Audio and Speech Processing Machine Learning Sound
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Discrete Speech Unit Extraction via Independent Component Analysis
por: Nakamura, Tomohiko, et al.
Publicado: (2025)

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

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

Multi-blank Transducers for Speech Recognition
por: Xu, Hainan, et al.
Publicado: (2022)

The Interspeech 2024 Challenge on Speech Processing Using Discrete Units
por: Chang, Xuankai, et al.
Publicado: (2024)

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

EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation
por: Richter, Julius, et al.
Publicado: (2024)

An Empirical Recipe for Universal Phone Recognition
por: Bharadwaj, Shikhar, et al.
Publicado: (2026)

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

Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study
por: Chen, Peikun, et al.
Publicado: (2024)

HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks
por: Dmitrieva, Ekaterina, et al.
Publicado: (2025)

[b]=[d]-[t]+[p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic
por: Choi, Kwanghee, et al.
Publicado: (2026)

Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspaces
por: Choi, Kwanghee, et al.
Publicado: (2026)

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

Discrete Unit based Masking for Improving Disentanglement in Voice Conversion
por: Lee, Philip H., et al.
Publicado: (2024)

Prosodic ABX: A Language-Agnostic Method for Measuring Prosodic Contrast in Speech Representations
por: Sun, Haitong, et al.
Publicado: (2026)

Drax: Speech Recognition with Discrete Flow Matching
por: Navon, Aviv, et al.
Publicado: (2025)

SSVD-O: Parameter-Efficient Fine-Tuning with Structured SVD for Speech Recognition
por: Wang, Pu, et al.
Publicado: (2026)

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

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

DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding
por: Shon, Suwon, et al.
Publicado: (2024)

High-Fidelity Speech Enhancement via Discrete Audio Tokens
por: Lanzendörfer, Luca A., et al.
Publicado: (2025)

Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition
por: Zeineldeen, Mohammad, et al.
Publicado: (2023)

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

Objective Evaluation of Prosody and Intelligibility in Speech Synthesis via Conditional Prediction of Discrete Tokens
por: Ulgen, Ismail Rasim, et al.
Publicado: (2025)

Speech Watermarking with Discrete Intermediate Representations
por: Ji, Shengpeng, et al.
Publicado: (2024)

Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages
por: Li, Chin-Jou, et al.
Publicado: (2025)

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

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

ToneUnit: A Speech Discretization Approach for Tonal Language Speech Synthesis
por: Tao, Dehua, et al.
Publicado: (2024)

Analyzing Speech Unit Selection for Textless Speech-to-Speech Translation
por: Duret, Jarod, et al.
Publicado: (2024)

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

Recovering Performance in Speech Emotion Recognition from Discrete Tokens via Multi-Layer Fusion and Paralinguistic Feature Integration
por: Sun, Esther, et al.
Publicado: (2026)

SpeakStream: Streaming Text-to-Speech with Interleaved Data
por: Bai, Richard He, et al.
Publicado: (2025)

Streaming Endpointer for Spoken Dialogue using Neural Audio Codecs and Label-Delayed Training
por: Udupa, Sathvik, et al.
Publicado: (2025)

RoVo: Robust Voice Protection Against Unauthorized Speech Synthesis with Embedding-Level Perturbations
por: Kim, Seungmin, et al.
Publicado: (2025)

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

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

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

Speech to Speech Synthesis for Voice Impersonation
por: Johnson, Bjorn, et al.
Publicado: (2026)