资源列表
davanci
- 基于达芬奇开发系统的音频压缩，包含语音采集，格式压缩等-DaVinci development of audio compression system, including voice capture, format, compression, etc.
furui-asr2-2
- "Toward Spontaneous Speech Recognition and Understanding" Sadaoki Furui
nordic-nRF24LE1
- Nordic Semiconductor，nRF24LE1无线语音门铃系统-Nordic Semiconductor, nRF24LE1 doorbell system wireless voice
jiyuxiaobobianhuandeyuyintezhentiqu
- 基于不变集多小波的语音特征参数提取研究 用小波变换替代傅立叶变换和梅尔滤波-Based on the invariant set Multiwavelet voice characteristic parameter extraction for research of wavelet transform and Fourier transform alternative Mel filter
AUDIO-WATERMARKING-USING-TRANSFORMATION-TECHNIQUE
- a thesis in audio watermarking using transformation tecniques very important
DTWvoice-recognition
- DTW语音识别算法,MATLAB对DTW算法编程，实现对语音的识别-voice recognition
BaiduASRAndTTS
- 利用百度语音api和NAudio写的一个语音识别、语音合成、语音录制的软件，学习够用了。(The software that uses Baidu voice API and NAudio for a speech recognition, speech synthesis, and voice recording software is sufficient to learn.)
espeak_1.36
- espeak语音生成库，内附有移植使用文档《espeak移植使用》-espeak speech generation library, containing transplanted using the document espeak transplant use
HMMDemo_Dbg
- HMM源代码，使用起来方便， 具有一定的使用价值-HMM source code, easy to use, has some value
ETSI_ES_202_212_software
- ETSI发布的用于研究分布式语音识别的前端降噪代码-ETSI issued for the study of Distributed Speech Recognition front Noise Code
26273_ansi_c_source_code_v6_5_0
- AMR-WB+是3GPP的标准音频和语音编码标准，采用C代码，关键是定点化的，可以直接移植到各种嵌入式平台。并且附有使用说明。方便开发-The fixed-point C code for AMR-WB+ codec with user guide .
festival-1.96-beta
- festival1.96开源的语音合成软件，是目前最新版本，可移植多平台-festival1.96 open source speech synthesis software, is the latest version of the portable multi-platform