Pith. sign in

REVIEW 5 cited by

MOSNet: Deep Learning based Objective Assessment for Voice Conversion

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1904.08352 v3 pith:ONY4GMGX submitted 2019-04-17 cs.SD cs.LGeess.AS

Chen-Chou Lo , Szu-Wei Fu , Wen-Chin Huang , Xin Wang , Junichi Yamagishi , Yu Tsao , Hsin-Min Wang This is my paper · ORCID
classification cs.SDcs.LGeess.AS
keywords humanmodelscorrelatedmosnetratingsresultsconversionproposed
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Existing objective evaluation metrics for voice conversion (VC) are not always correlated with human perception. Therefore, training VC models with such criteria may not effectively improve naturalness and similarity of converted speech. In this paper, we propose deep learning-based assessment models to predict human ratings of converted speech. We adopt the convolutional and recurrent neural network models to build a mean opinion score (MOS) predictor, termed as MOSNet. The proposed models are tested on large-scale listening test results of the Voice Conversion Challenge (VCC) 2018. Experimental results show that the predicted scores of the proposed MOSNet are highly correlated with human MOS ratings at the system level while being fairly correlated with human MOS ratings at the utterance level. Meanwhile, we have modified MOSNet to predict the similarity scores, and the preliminary results show that the predicted scores are also fairly correlated with human ratings. These results confirm that the proposed models could be used as a computational evaluator to measure the MOS of VC systems to reduce the need for expensive human rating.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation

    cs.CL 2025-07 conditional novelty 7.0 of 10

    With prompt engineering (audio concatenation plus in-context examples), large audio models rank speech synthesis systems in line with human preferences, reaching up to 0.91 Spearman correlation.

  2. Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers

    cs.SD 2026-07 conditional novelty 5.5 of 10

    A streaming encoder plus temporal and fully shared DiT-conditioned depth decoders converts semantic audio tokens to RVQ with constant memory and ~16× real-time on-device synthesis.

  3. A Survey of Automatic Evaluation Methods on Text, Visual and Speech Generations

    cs.CL 2025-06 conditional novelty 5.0 of 10

    A unified taxonomy and comparative meta-evaluation of automatic evaluation methods across text, vision, and speech generation, concluding that LLM-based evaluators dominate current practice.

  4. Visual-based spatial audio generation system for multi-speaker environments

    cs.MM 2025-02 reject novelty 5.0 of 10

    Using YOLOv8 face detection and Depth Anything depth estimation, this system converts mono dialogue into spatially placed binaural audio for multi-speaker video.

  5. SALF-MOS: Speaker Agnostic Latent Features Downsampled for MOS Prediction

    cs.SD 2025-06 reject novelty 4.0 of 10

    SALF-MOS, a compact U-Net-style model using frozen wav2vec features, claims state-of-the-art MOS prediction on four benchmarks with only 1,574 parameters.

Pith tools