Research on speech recognition algorithm based on HTK toolbox

The accuracy of automatic speech recognition (ASR) systems is generally evaluated using corpora of grammatically sound read speech or natural spontaneous speech. This prohibits an accurate estimation of the performance of the acoustic modeling part of ASR because the language modeling performance is inherently integrated in the overall performance metric. In this work, ASR and human speech recognition (HSR) accuracies are compared for null grammar sentences in different signal-to-noise ratios and vocabulary sizes-1000, 2000, 4000, and 8000. The results shed light on differences between ASR and HSR in relative significance of bottom-up word recognition and context awareness.

RETRACTED: Real time speech recognition algorithm on embedded system based on continuous Markov model

This study analyzes the effect of stress in human and automatic stressed speech processing tasks for speech collected from non-professional speakers. The database of 33 keywords is collected under five stress conditions, namely, neutral, angry, happy, sad and Lombard from fifteen speakers. The first study is to understand the ability to identify stress by human and automatic speech processing. The average performance of human stress classification is 59.44%. The average performance of automatic stress classifier using Vector Quantization (VQ) and Hidden Markov model (HMM) is 54.65% and 56.02%, respectively. The second study has been done to understand the effect of stress in human and automatic speech recognition. The average performance of human stressed speech recognition is 99.60%. The automatic stressed speech recognition performance using VQ and HMM is 82.42% and 76.79%, respectively. Even in the non-professional speakers scenario, human performance is better than automatic processing. Also, automatic processing seem to show considerable degradation in performance that warrant development of new methods to handle stress information.

Human speech recognition seems effortless, but so far it has been impossible to approach human performance by machines. Compared with human speech recognition (HSR), the error rates of state-of-the-art automatic speech recognition (ASR) systems are an order of magnitude larger (Lee, 2004; Moore, 2003; see also Scharenborg et al., 2005). This is true for many different speech recognition tasks in noise-free environments, but also (and especially) in noisy environments (Lippmann, 1997; Sroka & Braida, 2005; Wesker et al., 2005). The advantage for humans remains even in experiments that deprive humans from exploiting ‘semantic knowledge’ or ‘knowledge of the world’ that is not readily accessible for machines. It is well known that there are several recognition tasks in which machines outperform humans, such as the recognition of license plates or barcodes. Speech differs from license plates and bar codes in many respects, all of which help to make speech recognition by humans a fundamentally different skill. Probably the most important difference is that bar codes have been designed on purpose with machine recognition in mind, while speech as a medium for human-human communication has evolved over many millennia. Linguists have designed powerful tools for analyzing and describing speech, but we hardly begin to understand how humans process speech. Recent research suggests that conventional linguistic frameworks, which represent speech as a sequence of sounds, which in their turn can be represented by discrete symbols, fail to capture essential aspects of speech signals and, perhaps more importantly, of the neural processes involved in human speech understanding. All existing ASR systems are tributable to the beads-on-a-string representation (Ostendorf, 1999) invented by linguistics. But is quite possible –and some would say quite likely- that human speech understanding in not based on neural processes that map dynamically changing signals onto sequences of discrete symbols. Rather, it may well be that infants develop very different representations of speech during their language acquisition process. Language acquisition is a side effect of purposeful interaction between infants and their environment: infants learn to understand and respond to speech because it helps to fulfil a set of basic goals (Maslow, 1954; Wang, 2003). An extremely important need is being able to adapt to new situations (speakers, acoustic environments, words, etc.) Pattern recognisers, on the other hand, do not aim at the optimisation of ‘purposeful

An automatic speech recognition system based on the scene analysis account of auditory perception

Automatic Speech Recognition (ASR) has recorded appreciable progress both in technology and application. Despite this progress, there still exist wide performance gap between human speech recognition (HSR) and ASR which has inhibited its full adoption in real life situation. A brief review of research progress on Yorùbá Automatic Speech Recognition (ASR) is presented in this paper focusing of variability as factor contributing to performance gap between HSR and ASR with a view of x-raying the advances recorded, major obstacles, and chart a way forward for development of ASR for Yorùbá that is comparable to those of other tone languages and of developed nations. This is done through extensive surveys of literatures on ASR with focus on Yorùbá. Though appreciable progress has been recorded in advancement of ASR in the developed world, reverse is the case for most of the developing nations especially those of Africa. Yorùbá like most of languages in Africa lacks both human and materials resources needed for the development of functional ASR system much less taking advantage of its potentials benefits. Results reveal that attaining an ultimate goal of ASR performance comparable to human level requires deep understanding of variability factors.

Speech recognition is one of the important areas in digital speech processing. The study of speech recognition is a part of a quest for artificially intelligent machines that can hear and understand spoken information. The conventional methods for speech recognition are very complicated and time consuming. To apply fuzzy logic to speech recognition is a new attempt in digital speech processing. The approach proposed in the paper simplifies the algorithm in speech recognition and makes the real-time processing time shorter. The situation considered in this paper is the simplest, i.e., the situation of speaker dependence, small vocabulary and isolated words.

Combined speech enhancement and auditory modelling for robust distributed speech recognition

In this paper, based on the study of two speech recognition algorithms, two designs of speech recognition system are given to realize this isolated speech recognition mobile robot control system based on ARM9 processor. The speech recognition process includes pretreatment of speech signal, characteristic extrication, pattern matching and post-processing. Mel-Frequency cepstrum coefficients (MFCC) and linear prediction cepstrum coefficients (LPCC) are the two most common parameters. Through analysis and comparison the parameters, MFCC shows more noise immunity than LPCC, so MFCC is selected as the characteristic parameters. Both dynamic time warping (DTW) and hidden markov model (HMM) are commonly used algorithm. For the different characteristics of DTW and HMM recognition algorithm, two different programs were designed for mobile robot control system. The effect and speed of the two speech recognition system were analyzed and compared.

The aim of this study is to quantify the gap between the recognition performance of human listeners and an automatic speech recognition (ASR) system with special focus on intrinsic variations of speech, such as speaking rate and effort, altered pitch, and the presence of dialect and accent. Second, it is investigated if the most common ASR features contain all information required to recognize speech in noisy environments by using resynthesized ASR features in listening experiments. For the phoneme recognition task, the ASR system achieved the human performance level only when the signal-to-noise ratio (SNR) was increased by 15 dB, which is an estimate for the human-machine gap in terms of the SNR. The major part of this gap is attributed to the feature extraction stage, since human listeners achieve comparable recognition scores when the SNR difference between unaltered and resynthesized utterances is 10 dB. Intrinsic variabilities result in strong increases of error rates, both in human speech recognition (HSR) and ASR (with a relative increase of up to 120%). An analysis of phoneme duration and recognition rates indicates that human listeners are better able to identify temporal cues than the machine at low SNRs, which suggests incorporating information about the temporal dynamics of speech into ASR systems.

Algorithms for speech recognition can be characterized broadly as pattern recognition approaches and acoustic phonetic approaches. To date, the greatest degree of success in speech recognition has been obtained using pattern recognition paradigms. Thus, in this paper, we will be concerned primarily with showing how pattern recognition techniques have been applied to the problems of isolated word (or discrete utterance) recognition, connected word recognition, and continuous speech recognition. We will show that our understanding (and consequently the resulting recognizer performance) is best for the simplest recognition tasks and is considerably less well developed for large scale recognition systems.

The accurate recognition of speech is beneficial to the fields of machine translation and intelligent human–computer interaction. After briefly introducing speech recognition algorithms, this study proposed to recognize speech with a recurrent neural network (RNN) and adopted the connectionist temporal classification (CTC) algorithm to align input speech sequences and output text sequences forcibly. Simulation experiments compared the RNN-CTC algorithm with the Gaussian mixture model–hidden Markov model and convolutional neural network-CTC algorithms. The results demonstrated that the more training samples the speech recognition algorithm had, the higher the recognition accuracy of the trained algorithm was, but the training time consumption increased gradually; the more samples a trained speech recognition algorithm had to test, the lower the recognition accuracy and the longer the testing time. The proposed RNN-CTC speech recognition algorithm always had the highest accuracy and the lowest training and testing time among the three algorithms when the number of training and testing samples was the same.

In this paper, the improvements in the recently implemented Kannada speech recognition system is demonstrated in detail. The Kannada automatic speech recognition (ASR) system consists of ASR models which are created by using Kaldi, IVRS call flow and weather and agricultural commodity prices information databases. The task specific speech data used in the recently developed spoken dialogue system had high level of different background noises. The different types of noises present in collected speech data had an adverse effect on the on line and off line speech recognition performances. Therefore, to improve the speech recognition accuracy in Kannada ASR system, a noise reduction algorithm is developed which is a fusion of spectral subtraction with voice activity detection (SS-VAD) and minimum mean square error spectrum power estimator based on zero crossing (MMSE-SPZC) estimator. The noise elimination algorithm is added in the system before the feature extraction part. An alternative ASR models are created using subspace Gaussian mixture models (SGMM) and deep neural network (DNN) modeling techniques. The experimental results show that, the fusion of noise elimination technique and SGMM/DNN based modeling gives a better relative improvement of 7.68% accuracy compared to the recently developed GMM-HMM based ASR system. The least word error rate (WER) acoustic models could be used in spoken dialogue system. The developed spoken query system is tested from Karnataka farmers under uncontrolled environment.

Speech recognition has the potential to make technology more accessible to users. However, the accuracy of speech recognition remains limited for users with disabilities, including those with Down Syndrome, and the types and frequencies of recognition errors are poorly understood. This paper characterizes these problems, focusing on errors occurring when recognizing Down Syndrome speech. We analyze the transcripts from six speech recognition algorithms (Google, IBM, Otter.ai, Microsoft, AssemblyAI, OpenAI) using the audio content of 15 individuals with Down Syndrome (331 dialogues; 3428 words). Our analysis shows: (1) significant difference in speech recognition accuracy for people with Down Syndrome compared to neurotypical users; (2) the best algorithm for recognizing Down Syndrome speech is OpenAI (Word Accuracy = 67%; F1-score = 0.944); and (3) there is a prevalence of deletion errors followed by substitutions and insertions. These findings have implications for enhancing speech recognition for the next-generation voice assistants to meet the needs of users with Down Syndrome.

Acoustic features of speech include various spectral and temporal cues. It is known that temporal envelope plays a critical role for speech recognition by human listeners, while automated speech recognition (ASR) heavily relies on spectral analysis. This study compared sentence-recognition scores of humans and an ASR software, Dragon, when spectral and temporal-envelope cues were manipulated in background noise. Temporal fine structure of meaningful sentences was reduced by noise or tone vocoders. Three types of background noise were introduced: a white noise, a time-reversed multi-talker noise, and a fake-formant noise. Spectral information was manipulated by changing the number of frequency channels. With a 20-dB signal-to-noise ratio (SNR) and four vocoding channels, white noise had a stronger disruptive effect than the fake-formant noise. The same observation with 22 channels was made when SNR was lowered to 0 dB. In contrast, ASR was unable to function with four vocoding channels even with a 20-dB SNR. Its performance was least affected by white noise and most affected by the fake-formant noise. Increasing the number of channels, which improved the spectral resolution, generated non-monotonic behaviors for the ASR with white noise but not with colored noise. The ASR also showed highly improved performance with tone vocoders. It is possible that fake-formant noise affected the software's performance by disrupting spectral cues, whereas white noise affected performance by compromising speech segmentation. Overall, these results suggest that human listeners and ASR utilize different listening strategies in noise.