Speech synthesis and quality evaluation
The objective of this dissertation is to compare the results of objective Speech Quality Assessment (SQA) between human and synthetic speeches to verify the feasibility of using this method to identify if a speech is human-recorded. We also tried using speech synthesis and SQA to quantify the perfor...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/181485 |
| _version_ | 1826119414653648896 |
|---|---|
| author | Jiang, Xiaotong |
| author2 | Tan Yap Peng |
| author_facet | Tan Yap Peng Jiang, Xiaotong |
| author_sort | Jiang, Xiaotong |
| collection | NTU |
| description | The objective of this dissertation is to compare the results of objective Speech Quality Assessment (SQA) between human and synthetic speeches to verify the feasibility of using this method to identify if a speech is human-recorded. We also tried using speech synthesis and SQA to quantify the performance of a speech recognition task without original transcript. Human speech samples were taken from LibriSpeech, VCC 2018, and AISHELL-3, while synthetic speeches were generated by synthesizers called VITS, ChatTTS, and Tacotron 2. Preprocessing involved standardizing sampling rates and bit depths, followed by transcription with WhisperX to calculate Word Error Rate (WER) and Character Error Rate (CER). MOSNet, an SQA system was implemented to score speech quality, with results showing that MOSNet can accurately identify human speech within its training set but struggles with generalization outside it. Despite some correlation between MOSNet predictions and WERs, the results suggest that MOSNet alone cannot reliably assess speech recognition quality. The dissertation also conducted a subjective SQA test with 14 participants to compare human estimations with MOSNet evaluations, revealing challenges in distinguishing natural human speech from synthetic counterparts, and underscoring the importance of factors such as authentic accents and natural delivery in speech evaluations. |
| first_indexed | 2025-03-09T12:26:24Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/181485 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-03-09T12:26:24Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1814852024-12-06T15:49:16Z Speech synthesis and quality evaluation Jiang, Xiaotong Tan Yap Peng School of Electrical and Electronic Engineering EYPTan@ntu.edu.sg Computer and Information Science Engineering Speech quality assessment (SQA) MOSNet Human speech Synthetic speech WhisperX Word error rate (WER) Character error rate (CER) Speech synthesis Speech recognition The objective of this dissertation is to compare the results of objective Speech Quality Assessment (SQA) between human and synthetic speeches to verify the feasibility of using this method to identify if a speech is human-recorded. We also tried using speech synthesis and SQA to quantify the performance of a speech recognition task without original transcript. Human speech samples were taken from LibriSpeech, VCC 2018, and AISHELL-3, while synthetic speeches were generated by synthesizers called VITS, ChatTTS, and Tacotron 2. Preprocessing involved standardizing sampling rates and bit depths, followed by transcription with WhisperX to calculate Word Error Rate (WER) and Character Error Rate (CER). MOSNet, an SQA system was implemented to score speech quality, with results showing that MOSNet can accurately identify human speech within its training set but struggles with generalization outside it. Despite some correlation between MOSNet predictions and WERs, the results suggest that MOSNet alone cannot reliably assess speech recognition quality. The dissertation also conducted a subjective SQA test with 14 participants to compare human estimations with MOSNet evaluations, revealing challenges in distinguishing natural human speech from synthetic counterparts, and underscoring the importance of factors such as authentic accents and natural delivery in speech evaluations. Master's degree 2024-12-04T05:38:32Z 2024-12-04T05:38:32Z 2024 Thesis-Master by Coursework Jiang, X. (2024). Speech synthesis and quality evaluation. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/181485 https://hdl.handle.net/10356/181485 en application/pdf Nanyang Technological University |
| spellingShingle | Computer and Information Science Engineering Speech quality assessment (SQA) MOSNet Human speech Synthetic speech WhisperX Word error rate (WER) Character error rate (CER) Speech synthesis Speech recognition Jiang, Xiaotong Speech synthesis and quality evaluation |
| title | Speech synthesis and quality evaluation |
| title_full | Speech synthesis and quality evaluation |
| title_fullStr | Speech synthesis and quality evaluation |
| title_full_unstemmed | Speech synthesis and quality evaluation |
| title_short | Speech synthesis and quality evaluation |
| title_sort | speech synthesis and quality evaluation |
| topic | Computer and Information Science Engineering Speech quality assessment (SQA) MOSNet Human speech Synthetic speech WhisperX Word error rate (WER) Character error rate (CER) Speech synthesis Speech recognition |
| url | https://hdl.handle.net/10356/181485 |
| work_keys_str_mv | AT jiangxiaotong speechsynthesisandqualityevaluation |