| Paper: | SP-P7.9 | ||
| Session: | Topics in Speech Analysis | ||
| Time: | Wednesday, May 19, 13:00 - 15:00 | ||
| Presentation: | Poster | ||
| Topic: | Speech Processing: Speech Analysis | ||
| Title: | YET ANOTHER ACOUSTIC REPRESENTATION OF SPEECH SOUNDS | ||
| Authors: | Nobuaki Minematsu; University of Tokyo | ||
| Abstract: | This paper proposes yet another representation of speech sounds.The proposed modeling of speech can remove both multiplicative and linear transformational distortion from speech theoretically. With the method, speech sounds are represented without being affected by any static distortion inevitably involved in speech production/recording process, such as acoustic differences in microphone, room, line, speaker individuality including vocal tract length differences, and so forth. The method acoustically models not individual phones but their entire system, where only acoustic interrelation embedded in all the kinds of phones is focused. Since the method provides us with no absolute acoustic properties of a phone, it cannot recognize or synthesize even a single phone. On the contrary, the proposed method is shown to be able to be applied to pronunciation training effectively and reliably, where the proficiency of pronunciation is automatically estimated without acoustic models of the individual phones. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops