2022/06/15 by Adriana Stan, Stan, Adriana · 4 citations
Computer Science · Engineering · #Artificial intelligence #Audio and Speech Processing (eess.AS) #Computer science #Engineering #FOS: Electrical engineering #Machine learning #Natural Language Processing Techniques #Natural language processing #Process (computing) #Sample (material) #Speech Recognition and Synthesis #Speech recognition #Task (project management) #Topic Modeling #Track (disk drive) #Training set #Utterance #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2206.07448
published in arXiv (Cornell University) (Cornell University) · Accepted at Interspeech 2022 - VoiceMOS Challenge; 5 pages, 2 figures, 2 tables
arxiv created 2022/06/15 · openalex publication_date 2022/06/15 · arxiv updated 2022/06/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
This paper introduces the ZevoMOS entry to the main track of the VoiceMOS Challenge 2022. The ZevoMOS submission is based on a two-step finetuning of pretrained self-supervised learning (SSL) speech models. The first step uses a task of classifying natural versus synthetic speech, while the second step's task is to predict the MOS scores associated with each training sample. The results of the finetuning process are then combined with the confidence scores extracted from an automatic speech recognition model, as well as the raw embeddings of the training samples obtained from a wav2vec SSL speech model. The team id assigned to the ZevoMOS system within the VoiceMOS Challenge is T01. The submission was placed on the 14th place with respect to the system-level SRCC, and on the 9th place with respect to the utterance-level MSE. The paper also introduces additional evaluations of the intermediate results.