Comparing DTW-Based and HMM-Based Text- Dependent Speaker Verification Algorithms
نویسندگان
چکیده
Speaker verification is among the widely used biometrics which usually offer more secure authentication for user access than regular passwords. In this final project, we study the DTW-based and HMM-based speaker verification algorithms and a comparison between them is made based on their performances on our recorded dataset. The two feature sets commonly used in Speech Recognition Systems, LPC and MFCC, are also tested in this project. The experimental results show that in our recorded dataset, the DTW-based algorithm outperforms the HMM-based algorithm. Also, the LPC performs roughly the same as MFCC.
منابع مشابه
Using Exciting and Spectral Envelope Information and Matrix Quantization for Improvement of the Speaker Verification Systems
Speaker verification from talking a few words of sentences has many applications. Many methods as DTW, HMM, VQ and MQ can be used for speaker verification. We applied MQ for its precise, reliable and robust performance with computational simplicity. We also used pitch frequency and log gain contour for further improvement of the system performance.
متن کاملUsing Exciting and Spectral Envelope Information and Matrix Quantization for Improvement of the Speaker Verification Systems
Speaker verification from talking a few words of sentences has many applications. Many methods as DTW, HMM, VQ and MQ can be used for speaker verification. We applied MQ for its precise, reliable and robust performance with computational simplicity. We also used pitch frequency and log gain contour for further improvement of the system performance.
متن کاملSpeech detection for text-dependent speaker verification
The performance of text-dependent speaker verification systems degrades in noisy environment and when the true speaker utters words that are not part of the verification password. Energy-based voice activity detection (VAD) algorithms cannot distinguish between the true speaker’s speech and other background speech or between the speaker’s verification password and other words uttered by the spe...
متن کاملImprovement of speaker verification for Thai language
There are many strategies proposed for speaker verification (SV) system, both in text-dependent (fixed-text) and textindependent (free-text) domains. To convey an appropriate algorithm for Thai speech, several consecutively improvement methods are compared in this paper including the dynamic time warping (DTW) matching and Gaussian mixture model (GMM) based systems. We firstly developed a syste...
متن کاملAdvances on HMM-based text-dependent speaker verification
This paper presents recent development on text-dependent speaker verification technology in EU project PICASSO, which have improved the SV performance significantly. In the project we adopt HMM approach for pattern matching. In the paper we describes four different techniques, adaptive variance flooring, multiple use of enrolment sample, generalised competitive measurement for score normalisati...
متن کامل