activity
20242026
most citedA Survey on Speech Large Language Models for Understanding

6 citations · 7 across the 18 of their papers we have counts for

collaborators
Showing 2024 · eess.ASShow all

6 papers · 2 filters

eess.AS2024

Fast and High-Quality Auto-Regressive Speech Synthesis via Speculative Decoding

Bohan Li, Hankun Wang, Situo Zhang +2

The auto-regressive architecture, like GPTs, is widely used in modern Text-to-Speech (TTS) systems. However, it incurs substantial inference time, particularly due to the challenge…

eess.AS2024★ 6 cited

A Survey on Speech Large Language Models for Understanding

Jing Peng, Yucheng Wang, Bohan Li +9

Speech understanding is essential for interpreting the diverse forms of information embedded in spoken language, including linguistic, paralinguistic, and non-linguistic cues that…

eess.AS2024

LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec

Yiwei Guo, Zhihan Li, Chenpeng Du +3

Although discrete speech tokens have exhibited strong potential for language model-based speech generation, their high bitrates and redundant timbre information restrict the develo…

eess.AS2024

vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders

Yiwei Guo, Zhihan Li, Junjie Li +5

We propose a new speech discrete token vocoder, vec2wav 2.0, which advances voice conversion (VC). We use discrete tokens from speech self-supervised models as the content features…

eess.AS2024

The X-LANCE Technical Report for Interspeech 2024 Speech Processing Using Discrete Speech Unit Challenge

Yiwei Guo, Chenrun Wang, Yifan Yang +9

Discrete speech tokens have been more and more popular in multiple speech processing fields, including automatic speech recognition (ASR), text-to-speech (TTS) and singing voice sy…

eess.AS2024

Attention-Constrained Inference for Robust Decoder-Only Text-to-Speech

Hankun Wang, Chenpeng Du, Yiwei Guo +3

Recent popular decoder-only text-to-speech models are known for their ability of generating natural-sounding speech. However, such models sometimes suffer from word skipping and re…