Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910504605188096 |
|---|---|
| author | Rousso, Rotem Cohen, Eyal Keshet, Joseph Chodroff, Eleanor |
| author_facet | Rousso, Rotem Cohen, Eyal Keshet, Joseph Chodroff, Eleanor |
| contents | Forced alignment (FA) plays a key role in speech research through the automatic time alignment of speech signals with corresponding text transcriptions. Despite the move towards end-to-end architectures for speech technology, FA is still dominantly achieved through a classic GMM-HMM acoustic model. This work directly compares alignment performance from leading automatic speech recognition (ASR) methods, WhisperX and Massively Multilingual Speech Recognition (MMS), against a Kaldi-based GMM-HMM system, the Montreal Forced Aligner (MFA). Performance was assessed on the manually aligned TIMIT and Buckeye datasets, with comparisons conducted only on words correctly recognized by WhisperX and MMS. The MFA outperformed both WhisperX and MMS, revealing a shortcoming of modern ASR systems. These findings highlight the need for advancements in forced alignment and emphasize the importance of integrating traditional expertise with modern innovation to foster progress. Index Terms: forced alignment, phoneme alignment, word alignment |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_19363 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment Rousso, Rotem Cohen, Eyal Keshet, Joseph Chodroff, Eleanor Audio and Speech Processing Forced alignment (FA) plays a key role in speech research through the automatic time alignment of speech signals with corresponding text transcriptions. Despite the move towards end-to-end architectures for speech technology, FA is still dominantly achieved through a classic GMM-HMM acoustic model. This work directly compares alignment performance from leading automatic speech recognition (ASR) methods, WhisperX and Massively Multilingual Speech Recognition (MMS), against a Kaldi-based GMM-HMM system, the Montreal Forced Aligner (MFA). Performance was assessed on the manually aligned TIMIT and Buckeye datasets, with comparisons conducted only on words correctly recognized by WhisperX and MMS. The MFA outperformed both WhisperX and MMS, revealing a shortcoming of modern ASR systems. These findings highlight the need for advancements in forced alignment and emphasize the importance of integrating traditional expertise with modern innovation to foster progress. Index Terms: forced alignment, phoneme alignment, word alignment |
| title | Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.19363 |