In this paper, we present a novel Deep Triphone Embedding (DTE) representation derived from Deep Neural Network (DNN) to encapsulate the discriminative information present in the adjoining speech frames. DTEs are generated using a four hidden layer DNN with 3000 nodes in each hidden layer at the first-stage. This DNN is trained with the tied-triphone classification accuracy as an optimization criterion. Thereafter, we retain the activation vectors (3000) of the last hidden layer, for each speech MFCC frame, and perform dimension reduction to further obtain a 300 dimensional representation, which we termed as DTE. DTEs along with MFCC features are fed into a second-stage four hidden layer DNN, which is subsequently trained for the task of tied-triphone classification. Both DNNs are trained using tri-phone labels generated from a tied-state triphone HMM-GMM system, by performing a forced-alignment between the transcriptions and MFCC feature frames. We conduct the experiments on publicly available TED-LIUM speech corpus. The results show that the proposed DTE method provides an improvement of absolute 2.11% in phoneme recognition, when compared with a competitive hybrid tied-state triphone HMM-DNN system.
Voice trigger detection is an important task, which enables activating a voice assistant when a target user speaks a keyword phrase. A detector is typically trained on speech data independent of speaker information and used for the voice trigger detection task. However, such a speaker independent voice trigger detector typically suffers from performance degradation on speech from underrepresented groups, such as accented speakers. In this work, we propose a novel voice trigger detector that can use a small number of utterances from a target speaker to improve detection accuracy. Our proposed model employs an encoder-decoder architecture. While the encoder performs speaker independent voice trigger detection, similar to the conventional detector, the decoder predicts a personalized embedding for each utterance. A personalized voice trigger score is then obtained as a similarity score between the embeddings of enrollment utterances and a test utterance. The personalized embedding allows adapting to target speaker's speech when computing the voice trigger score, hence improving voice trigger detection accuracy. Experimental results show that the proposed approach achieves a 38% relative reduction in a false rejection rate (FRR) compared to a baseline speaker independent voice trigger model.
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 unsupervised 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.
Cross-lingual voice conversion (VC) is a task that aims to synthesize target voices with the same content while source and target speakers speak in different languages. Its challenge lies in the fact that the source and target data are naturally non-parallel, and it is even difficult to bridge the gaps between languages with no transcriptions provided. In this paper, we focus on knowledge transfer from monolin-gual ASR to cross-lingual VC, in order to address the con-tent mismatch problem. To achieve this, we first train a monolingual acoustic model for the source language, use it to extract phonetic features for all the speech in the VC dataset, and then train a Seq2Seq conversion model to pre-dict the mel-spectrograms. We successfully address cross-lingual VC without any transcription or language-specific knowledge for foreign speech. We experiment this on Voice Conversion Challenge 2020 datasets and show that our speaker-dependent conversion model outperforms the zero-shot baseline, achieving MOS of 3.83 and 3.54 in speech quality and speaker similarity for cross-lingual conversion. When compared to Cascade ASR-TTS method, our proposed one significantly reduces the MOS drop be-tween intra- and cross-lingual conversion.
Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the out-of-vocabulary problem, word models can be simpler to decode and may also be able to directly recognize semantically meaningful units. We present effective methods to train Sequence-to-Sequence models for direct word-level recognition (and character-level recognition) and show an absolute improvement of 4.4-5.0\% in Word Error Rate on the Switchboard corpus compared to prior work. In addition to these promising results, word-based models are more interpretable than character models, which have to be composed into words using a separate decoding step. We analyze the encoder hidden states and the attention behavior, and show that location-aware attention naturally represents words as a single speech-word-vector, despite spanning multiple frames in the input. We finally show that the Acoustic-to-Word model also learns to segment speech into words with a mean standard deviation of 3 frames as compared with human annotated forced-alignments for the Switchboard corpus.
Spoken keyword spotting (KWS) deals with the identification of keywords in audio streams and has become a fast-growing technology thanks to the paradigm shift introduced by deep learning a few years ago. This has allowed the rapid embedding of deep KWS in a myriad of small electronic devices with different purposes like the activation of voice assistants. Prospects suggest a sustained growth in terms of social use of this technology. Thus, it is not surprising that deep KWS has become a hot research topic among speech scientists, who constantly look for KWS performance improvement and computational complexity reduction. This context motivates this paper, in which we conduct a literature review into deep spoken KWS to assist practitioners and researchers who are interested in this technology. Specifically, this overview has a comprehensive nature by covering a thorough analysis of deep KWS systems (which includes speech features, acoustic modeling and posterior handling), robustness methods, applications, datasets, evaluation metrics, performance of deep KWS systems and audio-visual KWS. The analysis performed in this paper allows us to identify a number of directions for future research, including directions adopted from automatic speech recognition research and directions that are unique to the problem of spoken KWS.
In this paper, several works are proposed to address practical challenges for deploying RNN Transducer (RNN-T) based speech recognition system. These challenges are adapting a well-trained RNN-T model to a new domain without collecting the audio data, obtaining time stamps and confidence scores at word level. The first challenge is solved with a splicing data method which concatenates the speech segments extracted from the source domain data. To get the time stamp, a phone prediction branch is added to the RNN-T model by sharing the encoder for the purpose of force alignment. Finally, we obtain word-level confidence scores by utilizing several types of features calculated during decoding and from confusion network. Evaluated with Microsoft production data, the splicing data adaptation method improves the baseline and adaption with the text to speech method by 58.03% and 15.25% relative word error rate reduction, respectively. The proposed time stamping method can get less than 50ms word timing difference on average while maintaining the recognition accuracy of the RNN-T model. We also obtain high confidence annotation performance with limited computation cost.
The INTERSPEECH 2020 Deep Noise Suppression (DNS) Challenge is intended to promote collaborative research in real-time single-channel Speech Enhancement aimed to maximize the subjective (perceptual) quality of the enhanced speech. A typical approach to evaluate the noise suppression methods is to use objective metrics on the test set obtained by splitting the original dataset. While the performance is good on the synthetic test set, often the model performance degrades significantly on real recordings. Also, most of the conventional objective metrics do not correlate well with subjective tests and lab subjective tests are not scalable for a large test set. In this challenge, we open-sourced a large clean speech and noise corpus for training the noise suppression models and a representative test set to real-world scenarios consisting of both synthetic and real recordings. We also open-sourced an online subjective test framework based on ITU-T P.808 for researchers to reliably test their developments. We evaluated the results using P.808 on a blind test set. The results and the key learnings from the challenge are discussed. The datasets and scripts can be found here for quick access https://github.com/microsoft/DNS-Challenge.
This paper presents the Speech Technology Center (STC) speaker recognition (SR) systems submitted to the VOiCES From a Distance challenge 2019. The challenge's SR task is focused on the problem of speaker recognition in single channel distant/far-field audio under noisy conditions. In this work we investigate different deep neural networks architectures for speaker embedding extraction to solve the task. We show that deep networks with residual frame level connections outperform more shallow architectures. Simple energy based speech activity detector (SAD) and automatic speech recognition (ASR) based SAD are investigated in this work. We also address the problem of data preparation for robust embedding extractors training. The reverberation for the data augmentation was performed using automatic room impulse response generator. In our systems we used discriminatively trained cosine similarity metric learning model as embedding backend. Scores normalization procedure was applied for each individual subsystem we used. Our final submitted systems were based on the fusion of different subsystems. The results obtained on the VOiCES development and evaluation sets demonstrate effectiveness and robustness of the proposed systems when dealing with distant/far-field audio under noisy conditions.
Add to Chrome
Add to Firefox