Automatic Speech Recognition Decoder Research Articles

ETEH: Unified Attention-Based End-to-End ASR and KWS Architecture

Even though attention-based end-to-end (E2E) automatic speech recognition (ASR) models have been yielding state-of-the-art recognition accuracy, they still fall behind many of the ASR models deployed in the industry in some crucial functionalities such as online processing and precise timestamps generating. This weakness prevents attention-based E2E ASR models from being applied in several essential speech tasks, such as online speech recognition and keyword searching (KWS). In this paper, we describe our proposed unified attention-based E2E ASR and KWS architecture–ETEH, which supports, in one model, both online and offline ASR decoding modes, thus allowing for precise and reliable KWS. “ETE” stands for attention-based E2E modeling, whereas “H” represents the hybrid gaussian mixture model and hidden Markov model (GMM-HMM). As a combination of both, ETEH is an attention-based E2E ASR architecture which utilizes the frame-wise time alignment (FTA) generated by GMM-HMM ASR models. This FTA is used to better the model in two ways: first, it helps the monotonic attentions of ETEH models to capture more accurate word time stamps, thus resulting in lower latency for online decoding; second, it helps ETEH models to provide accurate and reliable KWS results. Furthermore, we are able to combine both offline and online modes in one ETEH model and establish a concise system by adopt the universal training strategy. ETEH is functional and unique, and to the best of our knowledge, we can hardly find a comparable single attention-based E2E ASR system as the baseline. To evaluate ASR accuracy and latency for ETEH, we use our previously proposed monotonic truncated attention (MTA) based online CTC/attention (OCA) ASR models as baselines. Experimental results show that ETEH ASR models gain significant improvement in ASR latency compared to the baseline. To evaluate KWS performance, we compare ETEH models with CTC-based KWS models. Results demonstrate that our ETEH models achieve significantly better KWS performance compared to the CTC baselines.

Prediction of speech intelligibility with DNN-based performance measures

This paper presents a speech intelligibility model based on automatic speech recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and a performance measure that estimates the word error rate from these probabilities. This model does not require the clean speech reference nor the word labels during testing as the ASR decoding step – which finds the most likely sequence of words given phoneme posterior probabilities – is omitted. The model is evaluated via the root-mean-squared error between the predicted and observed speech reception thresholds from eight normal-hearing listeners. The recognition task consists of identifying noisy words from a German matrix sentence test. The speech material was mixed with eight noise maskers covering different modulation types, from speech-shaped stationary noise to a single-talker masker. The prediction performance is compared to five established models and an ASR-model using word labels. Two combinations of features and networks were tested. Both include temporal information either at the feature level (amplitude modulation filterbanks and a feed-forward network) or captured by the architecture (mel-spectrograms and a time-delay deep neural network, TDNN). The TDNN model is on par with the DNN while reducing the number of parameters by a factor of 37; this optimization allows parallel streams on dedicated hearing aid hardware as a forward-pass can be computed within the 10 ms of each frame. The proposed model performs almost as well as the label-based model and produces more accurate predictions than the baseline models.

A Context-Aware Language Model to Improve the Speech Recognition in Air Traffic Control

Recognizing isolated digits of the flight callsign is an important and challenging task for automatic speech recognition (ASR) in air traffic control (ATC). Fortunately, the flight callsign is a kind of prior ATC knowledge and is available from dynamic contextual information. In this work, we attempt to utilize this prior knowledge to improve the performance of the callsign identification by integrating it into the language model (LM). The proposed approach is named context-aware language model (CALM), which can be applied for both the ASR decoding and rescoring phase. The proposed model is implemented with an encoder–decoder architecture, in which an extra context encoder is proposed to consider the contextual information. A shared embedding layer is designed to capture the correlations between the ASR text and contextual information. The context attention is introduced to learn discriminative representations to support the decoder module. Finally, the proposed approach is validated with an end-to-end ASR model on a multilingual real-world corpus (ATCSpeech). Experimental results demonstrate that the proposed CALM outperforms other baselines for both the ASR and callsign identification task, and can be practically migrated to a real-time environment.

A unified system for multilingual speech recognition and language identification

In this paper, a multilingual automatic speech recognition (ASR) and language identification (LID) system is designed. In contrast to conventional multilingual ASR systems, this paper takes advantage of the complementarity of the ASR and LID modules. First, the LID module contributes to the language adaptive training of the multilingual acoustic model. Then, the ASR decoding information acts as the confidence metric to balance the LID results. To simulate complex multilingual speech recognition situations, two types of LID strategies are conducted. For a multilingual speech recognition task in which only one language is contained in the speech stream, the language information can be directly determined based on utterance-level judgment. Under this condition, a segment-level statistical component and a two-stage update strategy are designed to assist in the utterance-level language classification. In another multilingual speech recognition task, where the speech stream contains multiple languages simultaneously, the Viterbi language state retrieval method based on neural network (NN) classification is used to perform dynamic detection of the language state. In both cases, the ASR decoding information is used to adjust the language classification results. Without prior knowledge of language identity information, the enhanced LID module achieves an accuracy of 99.3% for utterance-level language judgment and 92.4% for dynamic language detection, and the multilingual ASR system also provides performance comparable to that of monolingual ASR systems.

LAWS: Locality-AWare Scheme for Automatic Speech Recognition

Automatic Speech Recognition (ASR) systems are changing the way people interact with different applications on mobile devices. Fulfilling such user-interactivity requires not only a highly accurate, large-vocabulary recognition system, but also a real-time, energy-efficient solution. However, these ASR systems need high memory bandwidth and power budget, which may be impractical for most of small form-factor battery-operated devices. In this article, we propose two combined techniques implemented on top of a state-of-the-art ASR accelerator in order to significantly reduce its energy consumption and memory requirements. First, by leveraging the locality among consecutive segments of the speech signal, we develop a Locality-AWare-Scheme (LAWS) which exploits the on-chip recently-explored data while removing most of the off-chip accesses during the ASR's decoding process. As a result, we remove up to 60 percent of ASR's workload. As the second step, we introduce an approach to improve LAWS's effectiveness by selectively adapting the amount of ASR's workload, based on run-time feedback. In particular, we exploit the fact that the confidence of the ASR system varies along the recognition process. When confidence is high, the ASR system can be more restrictive and reduce the amount of work. The end design including both techniques provides a saving of more than 87 percent in the memory requests and 2.3x reduction in energy consumption, and a speedup of 2.1x with respect to a state-of-the-art baseline design.

End-to-End Speech Endpoint Detection Utilizing Acoustic and Language Modeling Knowledge for Online Low-Latency Speech Recognition

Speech endpoint detection (EPD) benefits from the decoder state features (DSFs) of online automatic speech recognition (ASR) system. However, the DSFs are obtained via the ASR decoding process, which can become prohibitively expensive especially in limited-resource scenarios such as the embedded devices. To address this problem, this paper proposes a language model (LM)-based end-of-utterance (EOU) predictor, which is trained to determine the framewise probabilities of the EOU token conditioned on the previous word history obtained from the 1-best decoding hypothesis of the ASR system in an end-to-end manner without an actual decoding process in the test step. Further, a novel end-to-end EPD strategy is presented to incorporate a phonetic embedding (PE)-based acoustic modeling knowledge and the proposed EOU predictor-based language modeling knowledge into an acoustic feature embedding (AFE)-based EPD approach within the recurrent neural networks (RNN)-based EPD framework. The proposed EPD algorithm is built upon the ensemble RNNs, which are independently trained for the three parts, which are the proposed LM-based EOU predictor, AFE-based EPD, and PE-based acoustic model (AM) in accordance with each target. The ensemble RNNs are concatenated at the level of the last hidden layers and then attached into the fully-connected deep neural networks (DNN)-based EPD classifier, which is trained in accordance with the ultimate EPD target. Thereafter, they are jointly retrained at the second step of the DNN training to yield the lower endpoint error. The proposed EPD framework was evaluated in terms of the endpoint accuracy and word error rate for the CHiME-3 and large-scale ASR tasks. The experimental results turn out that the proposed EPD algorithm efficiently outperforms the conventional EPD approaches.

Real-time Controlling Dynamics Sensing in Air Traffic System.

In order to obtain real-time controlling dynamics in air traffic system, a framework is proposed to introduce and process air traffic control (ATC) speech via radiotelephony communication. An automatic speech recognition (ASR) and controlling instruction understanding (CIU)-based pipeline is designed to convert the ATC speech into ATC related elements, i.e., controlling intent and parameters. A correction procedure is also proposed to improve the reliability of the information obtained by the proposed framework. In the ASR model, acoustic model (AM), pronunciation model (PM), and phoneme- and word-based language model (LM) are proposed to unify multilingual ASR into one model. In this work, based on their tasks, the AM and PM are defined as speech recognition and machine translation problems respectively. Two-dimensional convolution and average-pooling layers are designed to solve special challenges of ASR in ATC. An encoder–decoder architecture-based neural network is proposed to translate phoneme labels into word labels, which achieves the purpose of ASR. In the CIU model, a recurrent neural network-based joint model is proposed to detect the controlling intent and label the controlling parameters, in which the two tasks are solved in one network to enhance the performance with each other based on ATC communication rules. The ATC speech is now converted into ATC related elements by the proposed ASR and CIU model. To further improve the accuracy of the sensing framework, a correction procedure is proposed to revise minor mistakes in ASR decoding results based on the flight information, such as flight plan, ADS-B. The proposed models are trained using real operating data and applied to a civil aviation airport in China to evaluate their performance. Experimental results show that the proposed framework can obtain real-time controlling dynamics with high performance, only 4% word-error rate. Meanwhile, the decoding efficiency can also meet the requirement of real-time applications, i.e., an average 0.147 real time factor. With the proposed framework and obtained traffic dynamics, current ATC applications can be accomplished with higher accuracy. In addition, the proposed ASR pipeline has high reusability, which allows us to apply it to other controlling scenes and languages with minor changes.

System-independent ASR error detection and classification using Recurrent Neural Network

This paper addresses errors in continuous Automatic Speech Recognition (ASR) in two stages: error detection and error type classification. Unlike the majority of research in this field, we propose to handle the recognition errors independently from the ASR decoder. We first establish an effective set of generic features derived exclusively from the recognizer output to compensate for the absence of ASR decoder information. Then, we apply a variant Recurrent Neural Network (V-RNN) based models for error detection and error type classification. Such model learn additional information to the recognized word classification using label dependency. As a result, experiments on Multi-Genre Broadcast Media corpus have shown that the proposed generic features setup leads to achieve competitive performances, compared to state of the art systems in both tasks. Furthermore, we have shown that V-RNN trained on the proposed feature set appear to be an effective classifier for the ASR error detection with an Accuracy of 85.43%.

Automatic quality estimation for ASR system combination

Recognizer Output Voting Error Reduction (ROVER) has been widely used for system combination in automatic speech recognition (ASR). In order to select the most appropriate words to insert at each position in the output transcriptions, some ROVER extensions rely on critical information such as confidence scores and other ASR decoder features. This information, which is not always available, highly depends on the decoding process and sometimes tends to overestimate the real quality of the recognized words. In this paper we propose a novel variant of ROVER that takes advantage of ASR quality estimation (QE) for ranking the transcriptions at “segment level” instead of: i) relying on confidence scores, or ii) feeding ROVER with randomly ordered hypotheses. We first introduce an effective set of features to compensate for the absence of ASR decoder information. Then, we apply QE techniques to perform accurate hypothesis ranking at segment-level before starting the fusion process. The evaluation is carried out on two different tasks, in which we respectively combine hypotheses coming from independent ASR systems and multi-microphone recordings. In both tasks, it is assumed that the ASR decoder information is not available. The proposed approach significantly outperforms standard ROVER and it is competitive with two strong oracles that exploit prior knowledge about the real quality of the hypotheses to be combined. Compared to standard ROVER, the absolute WER improvements in the two evaluation scenarios range from 0.5% to 7.3%.

A SYSTEM COMBINATION FOR MALAY BROADCAST NEWS TRANSCRIPTION

In this paper, we propose a post decoding system combination approach for automatic transcribing Malay broadcast news. This approach combines the hypotheses produced by parallel automatic speech recognition (ASR) systems. Each ASR system uses different language models, one which is generic domain model and another is domain specific model. The main idea is to take advantage of different ASR knowledge to improve ASR decoding result. It uses the language score and time information to produce a 1-best lattice, and then rescore the 1-best lattice to get the most likely word sequence as the final output. The proposed approach was compared with conventional combination approach, the recognizer output voting error reduction (ROVER). Our proposed approach improved the word error rate (WER) from 33.9% to 30.6% with an average relative WER improvement of 9.74%, and it is better than the conventional ROVER approach.