Papers with Code 아카이브
Speech Tokenization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Speech tokenization is the task of representing speech signals as a sequence of discrete units. Such representations can be later used for various downstream tasks including automatic speech recognition, text-to-speech, etc. Such representation serves as the basis of Speech Language Models.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Factorized RVQ-GAN For Disentangled Speech Tokenization
Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework
Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models
Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English
TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation
Recent Advances in Discrete Speech Tokens: A Review
BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection
DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models
DM-Codec: Distilling Multimodal Representations for Speech Tokenization
Sylber: Syllabic Embedding Representation of Speech from Raw Audio
SyllableLM: Learning Coarse Semantic Units for Speech Language Models
Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT
LAST: Language Model Aware Speech Tokenization
STAB: Speech Tokenizer Assessment Benchmark
dMel: Speech Tokenization made Simple
Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing
Scaling Properties of Speech Language Models
BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data
RepCodec: A Speech Representation Codec for Speech Tokenization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.