类 型
12 篇文献
 
A Study on Sound Identification based on Spectral and Temporal Structures of Sinusoidal Trajectories  
0次引用 0 0
DEVELOPMENT OF VAD EVALUATION FRAMEWORK CENSREC-1-C AND INVESTIGATION OF RELATIONSHIP BETWEEN VAD AND SPEECH RECOGNITION PERFORMANCE  
ABSTRACT Voice activity detection (VAD) plays an important role in speech processing including speech recognition, speech enhancement, and speech coding in noisy environments. We developed an evaluati......
1次引用 0 0
Noisy speech recognition based on selection of multiple noise suppression methods using noise GMMs  
To achieve high recognition performance for a wide variety of noise and for a wide range of signal-to-noise ratio, this paper presents integration methods of four noise reduction algorithms: spectral ......
Annual Conference of the International Speech Communication Association  2006
0次引用 0 0
Effective post-processing for single-channel frequency-domain speech enhancement  
Conventional frequency-domain speech enhancement filters improve signal-to-noise ratio (SNR), but also produce speech distortions. This paper describes a novel post-processing algorithm devised for th......
International Conference on Multimedia Computing and Systems/International Conference on Multimedia and Expo  2008
0次引用 0 0
Comparative study on contributions of pitch-synchronization and peak-amplitude towards robustness issue of ASR  
We proposed previously a novel pitch-synchronous peak- amplitude (PS-PA) based feature extraction method, which achieved significant recognition accuracy for robust ASR (1). It is well-known that an a......
Annual Conference of the International Speech Communication Association  2006
0次引用 0 0
Temporal AM-FM combination for robust speech recognition  
A novel method for feature extraction from the frequency modulation (FM) in speech signals is proposed for robust speech recognition. To exploit of the multistream speech recognizers, each stream sho......
Speech Communication  2011
0次引用 0 0
Designing multiple distinctive phonetic feature extractors for canonicalization by using clustering technique  
Acoustic models of an HMM-based classifier include various types of hidden factors such as speaker-specific character- istics and acoustic environments. If there exist a canonicali- zation process tha......
Annual Conference of the International Speech Communication Association  2005
0次引用 0 0
A sampling-based environment population projection approach for rapid acoustic model adaptation  
We propose an environment population projection (EPP) approach for rapid acoustic model adaptation to reduce environment mismatches with limited amounts of adaptation data. This approach consists of t......
International Conference on Acoustics, Speech, and Signal Processing  2011
0次引用 0 0
Study of Noise Robust Voice Activity Detection Based on Periodic Component to Aperiodic Component Ratio  
This paper describes a study of noise robust voice activity detection (VAD) utilizing the periodic component to aperiodic component ratio (PAR). Although environmental sound changes dynamically in the......
3次引用 0 0
Performance Estimation of Speech Recognition System Under Noise Conditions Using Objective Quality Measures and Artificial Voice  
It is essential to ensure quality of service (QoS) when offering a speech recognition service for use in noisy environments. This means that the recognition performance in the target noise environment......
IEEE Transactions on Audio, Speech and Language Processing  2006
1次引用 0 0

1/2 第一页 上一页 1 2 下一页
Feedback
Feedback
Feedback
我想反馈:
排行榜