Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SpeechLMScore: Evaluating speech generation using speech language model

About

While human evaluation is the most reliable metric for evaluating speech generation systems, it is generally costly and time-consuming. Previous studies on automatic speech quality assessment address the problem by predicting human evaluation scores with machine learning models. However, they rely on supervised learning and thus suffer from high annotation costs and domain-shift problems. We propose SpeechLMScore, an unsupervised metric to evaluate generated speech using a speech-language model. SpeechLMScore computes the average log-probability of a speech signal by mapping it into discrete tokens and measures the average probability of generating the sequence of tokens. Therefore, it does not require human annotation and is a highly scalable framework. Evaluation results demonstrate that the proposed metric shows a promising correlation with human evaluation scores on different speech generation tasks including voice conversion, text-to-speech, and speech enhancement.

Soumi Maiti, Yifan Peng, Takaaki Saeki, Shinji Watanabe• 2022

Related benchmarks

TaskDatasetResultRank
Speech severity evaluationNKI-OC-VC nspk 15 (total)
Pearson Correlation Coefficient (r)0.7027
20
Speech severity evaluationNKI-SpeechRT nspk 54 (total)
Pearson Correlation Coefficient0.2392
20
Speech severity evaluationNKI-RUG-UMCG nspk 8 (total)
Pearson Correlation Coefficient (r)-0.3766
20
Showing 3 of 3 rows

Other info

Follow for update