|
|
Enhancing the effectiveness of automatic speech recognition
Zelinka, Petr ; Tučková,, Jana (referee) ; Nouza,, Jan (referee) ; Sigmund, Milan (advisor)
This work identifies the causes for unsatisfactory reliability of contemporary systems for automatic speech recognition when deployed in demanding conditions. The impact of the individual sources of performance degradation is documented and a list of known methods for their identification from the recognized signal is given. An overview of the usual methods to suppress the impact of the disruptive influences on the performance of speech recognition is provided. The essential contribution of the work is the formulation of new approaches to constructing acoustical models of noisy speech and nonstationary noise allowing high recognition performance in challenging conditions. The viability of the proposed methods is verified on an isolated-word speech recognizer utilizing several-hour-long recording of the real operating room background acoustical noise recorded at the Uniklinikum Marburg in Germany. This work is the first to identify the impact of changes in speaker’s vocal effort on the reliability of automatic speech recognition in the full vocal effort range (i.e. whispering through shouting). A new concept of a speech recognizer immune to the changes in vocal effort is proposed. For the purposes of research on changes in vocal effort, a new speech database, BUT-VE1, was created.
|
|
|
Enhancing the effectiveness of automatic speech recognition
Zelinka, Petr ; Tučková,, Jana (referee) ; Nouza,, Jan (referee) ; Sigmund, Milan (advisor)
This work identifies the causes for unsatisfactory reliability of contemporary systems for automatic speech recognition when deployed in demanding conditions. The impact of the individual sources of performance degradation is documented and a list of known methods for their identification from the recognized signal is given. An overview of the usual methods to suppress the impact of the disruptive influences on the performance of speech recognition is provided. The essential contribution of the work is the formulation of new approaches to constructing acoustical models of noisy speech and nonstationary noise allowing high recognition performance in challenging conditions. The viability of the proposed methods is verified on an isolated-word speech recognizer utilizing several-hour-long recording of the real operating room background acoustical noise recorded at the Uniklinikum Marburg in Germany. This work is the first to identify the impact of changes in speaker’s vocal effort on the reliability of automatic speech recognition in the full vocal effort range (i.e. whispering through shouting). A new concept of a speech recognizer immune to the changes in vocal effort is proposed. For the purposes of research on changes in vocal effort, a new speech database, BUT-VE1, was created.
|
|
|
Chassis of single purpose trailer MEGA EASY
Nouza, Pavel ; Peňáz, Jan (referee) ; Kašpárek, Jaroslav (advisor)
This diploma thesis deals with conceptual design chassis of tractor trailer with maximum weight 21 000 kg. First part of thesis introduces reader with division of constructal chassis elements. Next part deals with conceptual chassis design. The final part deals with strenght control of chassis frame, which has been designed in previous chapter. In last part of the thesis deals with stress control designed construction of the frame. Drawing documentation of chassis frame is a part of the thesis
|
|
|
Použití rozpoznávání řeči a rýmových testů k hodnocení českých systémů pro zpracování řeči
Vích, Robert ; Nouza, Jan
Speech intelligibility is the most important parameter of speech quality. In the contribution a new objective intelligibility assessment of speech processing algorithms, e.g., speech coding, synthesis, enhancement, conversion, is proposed. It is based on automatic speech recognition of rhyme tests. The idea is illustrated by comparison with listening evaluation of Czech rhyme tests and is applied for intelligibility assessment of Czech text-to-speech system and voice conversion.
|
|
|
Lze použít automatické rozpoznávání řeči k hodnocení kvality řeči?
Nouza, Jan ; Vích, Robert ; Vondra, Martin
In the contribution several case studies are presented in which automatic speech recognition was tested as a means for evaluating of speech quality, either human or synthetic. Usually, speech quality is measured by subjective listening tests. Our aim is to investigate, whether these tests, which request considerable amount of human time and experience, could be replaced or supplemented by techniques based on ASR.
|
|
| |
guest ::
RSS feed.