The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Emotions exhibited by a speaker can be detected by analyzing his/her speech, facial expressions and gestures or by combining these properties. This paper concentrates on determining the emotional state from speech signals. Various acoustic features such as energy, zero crossing rate(ZCR), fundamental frequency, Mel Frequency Cepstral Coefficients (MFCCs), etc are extracted for short term, overlapping...
Many pattern recognition problems involve characterizing samples with continuous labels instead of discrete categories. While regression models are suitable for these learning tasks, these labels are often discretized into binary classes to formulate the problem as a conventional classification task (e.g., classes with low versus high values). This methodology brings intrinsic limitations on the classification...
Despite the advances of information technology tools in the speech recognition task, the challenge to find a rapid and an efficient approach remains a principal research topic. In this paper, we apply the k-nearest neighbors (kNN) algorithm for Timit phoneme recognition with two models: crisp and fuzzy. Essentially, we explore the contribution of the fuzzy aspect for the crisp version of the kNN algorithm...
Whispered speech, as an alternative speaking style for normal phonated (non-whispered) speech, has received little attention in speech emotion recognition. Currently, speech emotion recognition systems are exclusively designed to process normal phonated speech and can result in significantly degraded performance on whispered speech because of the fundamental differences between normal phonated speech...
We present a joint noise and mask aware training strategy for deep neural network (DNN) based speech enhancement with sub-band features. First, based on the analysis of the previously proposed dynamic noise aware training approach tested on the wide-band (16 KHz) speech data, the full-band dynamic noise features cannot always improve the enhancement performance due to inaccurate noise estimation....
In recent years, we have seen a surge of interest in neuromorphic computing and its hardware design for cognitive applications. In this work, we present new neuromorphic architecture, circuit, and device co-designs that enable spike-based classification for speech recognition task. The proposed neuromorphic speech recognition engine supports a sparsely connected deep spiking network with coarse granularity,...
Signal processing front end for extracting the feature set is an important stage in any speaker recognition system. There are many types of features that are derived differently and have good impact on the recognition rate. This paper uses one of the techniques to extract the feature set from a speech signal known as Mel Frequency Cepstrum Coefficients (MFCCs) to represent the signal parametrically...
We propose a unified deep neural network (DNN) approach to achieve both high-quality enhanced speech and high-accuracy automatic speech recognition (ASR) simultaneously on the recent REverberant Voice Enhancement and Recognition Benchmark (RE-VERB) Challenge. These two goals are accomplished by two proposed techniques, namely DNN-based regression to enhance reverberant and noisy speech, followed by...
This paper investigates four single-channel speech dereverberation algorithms, i.e., two unsupervised approaches based on (i) spectral enhancement and (ii) linear prediction, as well as two supervised approaches relying on machine learning which incorporate deep neural networks to predict either (iii) the magnitude spectrogram or (iv) the ideal ratio mask. The relative merits of the four algorithms...
Aiming at language model (LM) adaptation for interactive speech transcription, this paper proposes a topic-based adaptation method using users' correction information. To infer the topic for each utterance in continuous speech, this method uses the correction information of history utterances adjacent to the current one. Perplexity is calculated for topic inference. Topic-related LMs are interpolated...
An investigation on classification of emotional speech cross different language families is proposed in this paper. Datasets on three languages, CDESD in Mandarin, Emo-DB in German, and DES in Danish are analyzed. With 2-D classifications on arousal-appraisal space, better recognition performances are observed in arousal dimension than in appraisal dimension. The classification rates in cross language...
Query-by-Example Spoken Term Detection(QbE-STD) has been a hot research topic in speech recognition field. While template representation is the key composition part of QbE-STD, many researchers have been committed to developing effective template representations to obtain the better performance. Gaussian posteriorgram has been widely used due to that the GMM model which generates the Gaussian posteriorgram...
In this work, the Fuzzy kNN (FkNN), an alternative of the standard kNN algorithm, is used for Timit phoneme recognition. Phoneme is the smallest unit that composes speech. For this reason, if phoneme recognition is performed, it can achieve a significant word and text recognition. Thus, the main idea consists on assigning phoneme membership to the data phonemes by measuring the distance to its kNN...
Studies show that multiple modal biometric systems for small-scale populations perform better than single modal biometric systems for robots's recognition. This paper establishes a new fusion method for multiple biometric feature identification which combines visual with auditory information. Before the fusion, speaker recognition based on vector quantization and face recognition based on sparse representation...
This paper proposes an end-to-end framework, namely fully convolutional recurrent network (FCRN) for handwritten Chinese text recognition (HCTR). Unlike traditional methods that rely heavily on segmentation, our FCRN is trained with online text data directly and learns to associate the pen-tip trajectory with a sequence of characters. FCRN consists of four parts: a path-signature layer to extract...
Speech is natural vocalized and primary means of communication. Speech is easy, hand-free, fast and do not require any technical knowledge. Communicating with computer using speech is simple and comfortable way for human being. Speech recognition system made this possible. The acoustic and language model for this system are available but mostly in English language. In India there are so many peoples...
Although Query-by-Example techniques based on Euclidean distance in a multidimensional feature space have proved to be effective for image databases, this approach cannot be effectively applied to video since the number of dimensions would be massive due to the richness and complexity of video data. The above issue has been addressed in two recent solutions, namely Deterministic Quantization (DQ)...
Deep neural networks (DNNs) have tremendously improved the performance of automatic speech recognition (ASR). On the other hand, end-to-end speech recognition system can achieve state-of-the-art performance using Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) and Connectionist Temporal Classification (CTC) method for unsegmented sequence data. In this paper, we therefor propose a lightweight...
A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetic discriminate/speaker discriminate DNN as a feature extractor for speaker verification has shown promising results. The extracted frame-level (bottleneck, posterior or d-vector) features are equally weighted and aggregated to compute an utterance-level speaker representation...
Long short-term memory (LSTM) recurrent neural network based language models are known to improve speech recognition performance. However, significant effort is required to optimize network structures and training configurations. In this study, we automate the development process using evolutionary algorithms. In particular, we apply the covariance matrix adaptation-evolution strategy (CMA-ES), which...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.