A novel 2kb/s waveform interpolation speech coder based on non-negative matrix factorization
نویسندگان
چکیده
In this paper, a 2kb/s Waveform Interpolation speech coder is proposed based on non-negative matrix factorization (NMF). In characteristic waveforms (CWs) decomposition, band-partitioning initialization constraints were set to basis vectors before NMF was carried out. This decomposition method only requires speech signal from the current frame, and can yield high decomposition quality with low computational complexity. Besides, the high dimensional CWs matrix can be expressed by the low dimensional coding matrix, and this has facilitated the CWs quantization. The listening test shows that the proposed 2kb/s NMF-WI coder can give smooth speech with quality close to 2.4kb/s
منابع مشابه
A Low-complexity Improved WI Speech Coding at 2kbps
The waveform interpolation (WI) speech coding presents a good performance at low bit rate. However, the algorithm has a very high complexity in computation. In this paper, a low-complexity improved waveform interpolation speech coder at 2kbps is proposed. The improved coding scheme has greatly reduced the computational complexity and improved the reconstructed speech quality by using various te...
متن کاملStatistical Approaches to Excitation Modeling in HMM-Based Speech Synthesis
In our previous study, we proposed the waveform interpolation (WI) approach to model the excitation signals for hidden Markov model (HMM)-based speech synthesis. This letter presents several techniques to improve excitation modeling within the WI framework. We propose both the time domain and frequency domain zero padding techniques to reduce the spectral distortion inherent in the synthesized ...
متن کاملA new low bit rate speech coder based on intraframe waveform interpolation
A new characteristic waveform (CW) interpolation coder is proposed in this paper. In the proposed coder, two characteristic waveforms are extracted from LPC residual signal at each frame. The Waveform Interpolation (WI) is operated within the frame. In the novel WI, variable dimension vector quantization (VDVQ) and power vector quantization are proposed and the low frequency band (LFB) and high...
متن کاملWideband Speech Coding at 4 kbps using Waveform Interpolation
In this paper we present a new low rate, wideband speech coder operating at 4 kbps and based on Waveform Interpolation (WI). An outline of WI speech coding is provided together with a description of its adaptation to wideband speech. Particular emphasis is placed on the quantisation of the WI parameters. Included is a detailed analysis of the quantisation requirements for the Line Spectral Freq...
متن کاملVoice-based Age and Gender Recognition using Training Generative Sparse Model
Abstract: Gender recognition and age detection are important problems in telephone speech processing to investigate the identity of an individual using voice characteristics. In this paper a new gender and age recognition system is introduced based on generative incoherent models learned using sparse non-negative matrix factorization and atom correction post-processing method. Similar to genera...
متن کامل