出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：This paper presents a baseline digits speech recognizer for Hindi language. The recordingenvironment is different for all speakers, since the data is collected in their respective homes.The different environment refers to vehicle horn noises in some road facing rooms, internalbackground noises in some rooms like opening doors, silence in some rooms etc. All theserecordings are used for training acoustic model. The Acoustic Model is trained on 8 speakers’audio data. The vocabulary size of the recognizer is 10 words. HTK toolkit is used for buildingacoustic model and evaluating the recognition rate of the recognizer. The efficiency of therecognizer developed on recorded data, is shown at the end of the paper and possible directionsfor future research work are suggested.
