اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدFlexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios
170
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Often, the storage and computational constraints of embeddeddevices demand that a single on-device ASR model serve multiple use-cases / domains. In this paper, we propose aFlexibleTransducer(FlexiT) for on-device automatic speech recognition to flexibly deal with multiple use-cases / domains with different accuracy and latency requirements. Specifically, using a single compact model, FlexiT provides a fast response for voice commands, and accurate transcription but with more latency for dictation. In order to achieve flexible and better accuracy and latency trade-offs, the following techniques are used. Firstly, we propose using domain-specific altering of segment size for Emformer encoder that enables FlexiT to achieve flexible de-coding. Secondly, we use Alignment Restricted RNNT loss to achieve flexible fine-grained control on token emission latency for different domains. Finally, we add a domain indicator vector as an additional input to the FlexiT model. Using the combination of techniques, we show that a single model can be used to improve WERs and real time factor for dictation scenarios while maintaining optimal latency for voice commands use-cases
قيم البحث
اقرأ أيضاً
As speech-enabled devices such as smartphones and smart speakers become increasingly ubiquitous, there is growing interest in building automatic speech recognition (ASR) systems that can run directly on-device; end-to-end (E2E) speech recognition mod
els such as recurrent neural network transducers and their variants have recently emerged as prime candidates for this task. Apart from being accurate and compact, such systems need to decode speech with low user-perceived latency (UPL), producing words as soon as they are spoken. This work examines the impact of various techniques - model architectures, training criteria, decoding hyperparameters, and endpointer parameters - on UPL. Our analyses suggest that measures of model size (parameters, input chunk sizes), or measures of computation (e.g., FLOPS, RTF) that reflect the models ability to process input frames are not always strongly correlated with observed UPL. Thus, conventional algorithmic latency measurements might be inadequate in accurately capturing latency observed when models are deployed on embedded devices. Instead, we find that factors affecting token emission latency, and endpointing behavior have a larger impact on UPL. We achieve the best trade-off between latency and word error rate when performing ASR jointly with endpointing, while utilizing the recently proposed alignment regularization mechanism.
End-to-end models are favored in automatic speech recognition (ASR) because of its simplified system structure and superior performance. Among these models, recurrent neural network transducer (RNN-T) has achieved significant progress in streaming on
-device speech recognition because of its high-accuracy and low-latency. RNN-T adopts a prediction network to enhance language information, but its language modeling ability is limited because it still needs paired speech-text data to train. Further strengthening the language modeling ability through extra text data, such as shallow fusion with an external language model, only brings a small performance gain. In view of the fact that Mandarin Chinese is a character-based language and each character is pronounced as a tonal syllable, this paper proposes a novel cascade RNN-T approach to improve the language modeling ability of RNN-T. Our approach firstly uses an RNN-T to transform acoustic feature into syllable sequence, and then converts the syllable sequence into character sequence through an RNN-T-based syllable-to-character converter. Thus a rich text repository can be easily used to strengthen the language model ability. By introducing several important tricks, the cascade RNN-T approach surpasses the character-based RNN-T by a large margin on several Mandarin test sets, with much higher recognition quality and similar latency.
It is already known that both auditory and visual stimulus is able to convey emotions in human mind to different extent. The strength or intensity of the emotional arousal vary depending on the type of stimulus chosen. In this study, we try to invest
igate the emotional arousal in a cross-modal scenario involving both auditory and visual stimulus while studying their source characteristics. A robust fractal analytic technique called Detrended Fluctuation Analysis (DFA) and its 2D analogue has been used to characterize three (3) standardized audio and video signals quantifying their scaling exponent corresponding to positive and negative valence. It was found that there is significant difference in scaling exponents corresponding to the two different modalities. Detrended Cross Correlation Analysis (DCCA) has also been applied to decipher degree of cross-correlation among the individual audio and visual stimulus. This is the first of its kind study which proposes a novel algorithm with which emotional arousal can be classified in cross-modal scenario using only the source audio and visual signals while also attempting a correlation between them.
Recent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem. In this study, we provide a family of efficient neural network architectures f
or general purpose audio source separation while focusing on multiple computational aspects that hinder the application of neural networks in real-world scenarios. The backbone structure of this convolutional network is the SUccessive DOwnsampling and Resampling of Multi-Resolution Features (SuDoRM-RF) as well as their aggregation which is performed through simple one-dimensional convolutions. This mechanism enables our models to obtain high fidelity signal separation in a wide variety of settings where variable number of sources are present and with limited computational resources (e.g. floating point operations, memory footprint, number of parameters and latency). Our experiments show that SuDoRM-RF models perform comparably and even surpass several state-of-the-art benchmarks with significantly higher computational resource requirements. The causal variation of SuDoRM-RF is able to obtain competitive performance in real-time speech separation of around 10dB scale-invariant signal-to-distortion ratio improvement (SI-SDRi) while remaining up to 20 times faster than real-time on a laptop device.
This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervi
sed training. Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc. A new forced alignment and segmentation pipeline is proposed to create sentence segments suitable for speech recognition training, and to filter out segments with low-quality transcription. For system training, GigaSpeech provides five subsets of different sizes, 10h, 250h, 1000h, 2500h, and 10000h. For our 10,000-hour XL training subset, we cap the word error rate at 4% during the filtering/validation stage, and for all our other smaller training subsets, we cap it at 0%. The DEV and TEST evaluation sets, on the other hand, are re-processed by professional human transcribers to ensure high transcription quality. Baseline systems are provided for popular speech recognition toolkits, namely Athena, ESPnet, Kaldi and Pika.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
