paper-with-me

Papers

UniTTS: Residual Learning of Unified Embedding Space for Speech Style Control

2021-06-21 · Minsu Kang, Sungjae Kim, Injung Kim

We propose a novel high-fidelity expressive speech synthesis model, UniTTS, that learns and controls overlapping style attributes avoiding interference. UniTTS represents multiple style attributes in a single unified embedding space by the residuals between the phoneme embeddings before and after applying the attributes. The proposed method is especially effective in controlling multiple attributes that are difficult to separate cleanly, such as speaker ID and emotion, because it minimizes redundancy when adding variance in speaker ID and emotion, and additionally, predicts duration, pitch, and energy based on the speaker ID and emotion. In experiments, the visualization results exhibit that the proposed methods learned multiple attributes harmoniously in a manner that can be easily separated again. As well, UniTTS synthesized high-fidelity speech signals controlling multiple style attributes. The synthesized speech samples are presented at https://anonymous-authors2022.github.io/paper_works/UniTTS/demos/.

📄 PDF Abstract BibTeX arXiv:2106.11171

Code (0)

등록된 구현이 없습니다.

Tasks

Expressive Speech SynthesisSpeech Synthesis

Similar Papers 제목 키워드 기반

UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information

2025-05-23 · Rui Wang, Qianguo Sun, Tianrong Chen, Zhiyun Zeng 외

The emergence of multi-codebook neutral audio codecs such as Residual Vector Quantization (RVQ) and Group Vector Quantization (GVQ) has significantly advanced Large-Language-Model (LLM) based Text-to-Speech (TTS) systems…

Large Language ModelQuantizationtext-to-speechText to Speech

Residual Information in Deep Speaker Embedding Architectures

2023-02-06 · Adriana Stan

Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to class…

TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment

2025-06-01 · Taesoo Kim, Jong Hwan Ko

Recent advances in speech-enabled language models have shown promising results in building intelligent voice assistants. However, most existing approaches rely on large-scale paired speech-text data and extensive computa…

ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining

2026-03-30 · Anuj Diwan, Eunsol Choi, David Harwath arxiv

We introduce ParaSpeechCLAP, a family of dual-encoder models that map speech and text style captions into a shared embedding space, supporting rich intrinsic (speaker-level) and situational (utterance-level) descriptors,…

SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models

2023-08-31 · Xin Zhang, Dong Zhang, ShiMin Li, Yaqian Zhou 외

Current speech large language models build upon discrete speech representations, which can be categorized into semantic tokens and acoustic tokens. However, existing speech tokens are not specifically designed for speech…

DecoderLanguage ModelingLanguage ModellingQuantization+2