Difference between revisions of "Projects:2019s2-24101 Improving Usability and User Interaction with KALDI Open- Source Speech Recogniser"
| Line 2: | Line 2: | ||
This project is about improving the word error rate in audio transcription by KALDI. KALDI is used to transcript audio using various language and acoustic models. | This project is about improving the word error rate in audio transcription by KALDI. KALDI is used to transcript audio using various language and acoustic models. | ||
The previous work in improving the word error rate is done by improving the language and acoustic models of audio. our project focus on improving the input signal quality by audio processing using the software HARK. HARK works on Missing feature theory and eliminates noise by various algorithms. | The previous work in improving the word error rate is done by improving the language and acoustic models of audio. our project focus on improving the input signal quality by audio processing using the software HARK. HARK works on Missing feature theory and eliminates noise by various algorithms. | ||
| − | + | ---- | |
| + | '''Background''' | ||
| + | Speech transcription is a process done by computer hardware and software to transform an audio input into a text output. | ||
| + | Speech transcription increases the accessibility and understand-ability of voice recordings and other audio materials for many different use cases. | ||
| + | ---- | ||
'''Project team | '''Project team | ||
Project students''' | Project students''' | ||
| Line 8: | Line 12: | ||
Pengyue Song | Pengyue Song | ||
---- | ---- | ||
| − | |||
'''Supervisors''' | '''Supervisors''' | ||
Dr. Said- Al- Sarawi | Dr. Said- Al- Sarawi | ||
DSTG Dr Ahmad Hashemi-Sakhtsari | DSTG Dr Ahmad Hashemi-Sakhtsari | ||
| − | + | ---- | |
| − | |||
'''Method''' | '''Method''' | ||
---- | ---- | ||
Revision as of 04:17, 7 October 2019
Introduction This project is about improving the word error rate in audio transcription by KALDI. KALDI is used to transcript audio using various language and acoustic models. The previous work in improving the word error rate is done by improving the language and acoustic models of audio. our project focus on improving the input signal quality by audio processing using the software HARK. HARK works on Missing feature theory and eliminates noise by various algorithms.
Background Speech transcription is a process done by computer hardware and software to transform an audio input into a text output. Speech transcription increases the accessibility and understand-ability of voice recordings and other audio materials for many different use cases.
Project team Project students Riya Parth Dube Pengyue Song
Supervisors Dr. Said- Al- Sarawi
DSTG Dr Ahmad Hashemi-Sakhtsari
Method
Results
Conclusion
References 1 The HARK Documentation available online at https://www.hark.jp/document/3.0.0/hark-document-en/sect0002.html 2 The KALDI Decoder online available at https://kaldi-asr.org/ 3 D. Povey, “KALDI – Home”, KALDI, n.d. [Online] Available at: http://kaldi-asr.org/ [Accessed: September 2019].
