Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding
This work addresses speed bottlenecks in speech synthesis systems, offering a flexible trade-off between speed and quality, though it is incremental as it builds on existing codec-based methods.
The paper tackles the problem of slow inference in codec-based speech synthesis by proposing a multi-token prediction and speculative decoding method, achieving a 4-5 times reduction in token prediction time with minimal quality loss.
The goal of this paper is to accelerate codec-based speech synthesis systems with minimum sacrifice to speech quality. We propose an enhanced inference method that allows for flexible trade-offs between speed and quality during inference without requiring additional training. Our core idea is to predict multiple tokens per inference step of the AR module using multiple prediction heads, resulting in a linear reduction in synthesis time as the number of heads increases. Furthermore, we introduce a novel speculative decoding technique that utilises a Viterbi-based algorithm to select the optimal sequence of generated tokens at each decoding step. In our experiments, we demonstrate that the time required to predict each token is reduced by a factor of 4 to 5 compared to baseline models, with minimal quality trade-off or even improvement in terms of speech intelligibility. Audio samples are available at: multpletokensprediction.github.io/multipletokensprediction.github.io/.