Evaluating Text-to-Speech Synthesis from a Large Discrete Token-based Speech Language Model

TL;DR

This paper evaluates a large discrete token-based speech language model for text-to-speech synthesis, highlighting its strengths in prosody and naturalness while identifying limitations in intelligibility and speaker consistency.

Contribution

It provides a comprehensive evaluation of discrete token-based SLMs for TTS, establishing benchmarks and analyzing their capabilities and limitations.

Findings

Strength in generating varied prosody and spontaneous speech.

Higher naturalness and context appropriateness compared to traditional TTS.

Modest improvements in robustness with larger models.

Abstract

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.