Evaluating Text-to-Speech Synthesis from a Large Discrete Token-based Speech Language Model
원문 초록
Recent advances in generative language modeling applied to discrete speech tokens presented a new avenue for text-to-speech (TTS) synthesis. These speech language models (SLMs), similarly to their textual counterparts, are scalable, probabilistic, and context-aware. While they can produce diverse and natural outputs, they sometimes face issues such as unintelligibility and the inclusion of non-speech noises or hallucination. As the adoption of this innovative paradigm in speech synthesis increases, there is a clear need for an in-depth evaluation of its capabilities and limitations. In this paper, we evaluate TTS from a discrete token-based SLM, through both automatic metrics and listening tests. We examine five key dimensions: speaking style, intelligibility, speaker consistency, prosodic variation, spontaneous behaviour. Our results highlight the model's strength in generating varied prosody and spontaneous outputs. It is also rated higher in naturalness and context appropriateness in listening tests compared to a conventional TTS. However, the model's performance in intelligibility and speaker consistency lags behind traditional TTS. Additionally, we show that increasing the scale of SLMs offers a modest boost in robustness. Our findings aim to serve as a benchmark for future advancements in generative SLMs for speech synthesis.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Mlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State Transducers
EmoNews: A Spoken Dialogue System for Expressive News Conversations
ByDeWay: Boost Your multimodal LLM with DEpth prompting in a Training-Free Way
LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization
ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.