This paper proposes two novel variants of neural reprogramming to enhance wake word recognition in streaming end-to-end ASR models without updating model weights. The first, "trigger-frame reprogramming", prepends the input speech feature sequence with the learned trigger-frames of the target wake word to adjust ASR model’s hidden states for improved wake word recognition. The second, "predictor-state initialization", trains only the initial state vectors (cell and hidden states) of the LSTMs in the prediction network. When applying to a baseline LibriSpeech Emformer RNN-T model with a 98% wake word verification false rejection rate (FRR) on unseen wake words, the proposed approaches achieve 76% and 97% relative FRR reductions with no increase on false acceptance rate. In-depth characteristic analyses of the proposed approaches are also conducted to provide deeper insights. These approaches offer an effective hot-fixing methods to improve wake word recognition performance in deployed production ASR models without the need for model updates.

We propose an approach for continuous prediction of turn-taking and backchanneling locations in spoken dialogue by fusing a neural acoustic model with a large language model (LLM). Experiments on the Switchboard human-human conversation dataset demonstrate that our approach consistently outperforms the baseline models with single modality. We also develop a novel multi-task instruction fine-tuning strategy to further benefit from LLM-encoded knowledge for understanding the tasks and conversational contexts, leading to additional improvements. Our approach demonstrates the potential of combined LLMs and acoustic models for a more natural and conversational interaction between humans and speech-enabled AI agents.

Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands. The endpoint detector has to trade-off between accuracy and latency, since waiting longer reduces the cases of users being cut-off early. We propose a novel two-pass solution for endpointing, where the utterance endpoint detected from a first pass endpointer is verified by a 2nd-pass model termed EP Arbitrator. Our method improves the trade-off between early cut-offs and latency over a baseline endpointer, as tested on datasets including voice-assistant transactional queries, conversational speech, and the public SLURP corpus. We demonstrate that our method shows improvements regardless of the first-pass EP model used.

Current endpointing (EP) solutions learn in a supervised framework, which does not allow the model to incorporate feedback and improve in an online setting. Also, it is common practice to utilize costly grid-search to find the best configuration for an endpointing model. In this paper, we aim to provide a solution for adaptive endpointing by proposing an efficient method for choosing an optimal endpointing configuration given utterance-level audio features in an online setting, while avoiding hyperparameter grid-search. Our method does not require ground truth labels, and uses only online learning from reward signals. Specifically, we propose a deep contextual multi-armed bandit-based approach, combining the representational power of neural networks with the action exploration behavior of Thomp-son modeling algorithms. We compare our approach to several baselines, and show that our deep bandit models also succeed in reducing early cutoff errors while maintaining low latency.

Automatic speech recognition (ASR) models with low-footprint are increasingly being deployed on edge devices for conversational agents, which enhances privacy. We study the problem of federated continual incremental learning for recurrent neural network-transducer (RNN-T) ASR models in the privacy-enhancing scheme of learning on-device, without access to ground truth human transcripts or machine transcriptions from a stronger ASR model. In particular, we study the performance of a self-learning based scheme, with a paired teacher model updated through an exponential moving average of ASR models. Further, we propose using possibly noisy weak-supervision signals such as feedback scores and natural language understanding semantics determined from user behavior across multiple turns in a session of interactions with the conversational agent. These signals are leveraged in a multitask policy-gradient training approach to improve the performance of self-learning for ASR. Finally, we show how catastrophic forgetting can be mitigated by combining on-device learning with a memory-replay approach using selected historical datasets. These innovations allow for 10% relative improvement in WER on new use cases with minimal degradation on other test sets in the absence of strong-supervision signals such as ground-truth transcriptions.

We propose a novel approach for ASR N-best hypothesis rescoring with graph-based label propagation by leveraging cross-utterance acoustic similarity. In contrast to conventional neural language model (LM) based ASR rescoring/reranking models, our approach focuses on acoustic information and conducts the rescoring collaboratively among utterances, instead of individually. Experiments on the VCTK dataset demonstrate that our approach consistently improves ASR performance, as well as fairness across speaker groups with different accents. Our approach provides a low-cost solution for mitigating the majoritarian bias of ASR systems, without the need to train new domain- or accent-specific models.

As for other forms of AI, speech recognition has recently been examined with respect to performance disparities across different user cohorts.One approach to achieve fairness in speech recognition is to (1) identify speaker cohorts that suffer from subpar performance and (2) apply fairness mitigation measures targeting the cohorts discovered.In this paper, we report on initial findings with both discovery and mitigation of performance disparities using data from a product-scale AI assistant speech recognition system.We compare cohort discovery based on geographic and demographic information to a more scalable method that groups speakers without human labels, using speaker embedding technology.For fairness mitigation, we find that oversampling of underrepresented cohorts, as well as modeling speaker cohort membership by additional input variables, reduces the gap between top-and bottom-performing cohorts, without deteriorating overall recognition accuracy.

Spoken language understanding (SLU) systems extract both text transcripts and semantics associated with intents and slots from input speech utterances.SLU systems usually consist of (1) an automatic speech recognition (ASR) module, (2) an interface module that exposes relevant outputs from ASR, and (3) a natural language understanding (NLU) module.Interfaces in SLU systems carry information on text transcriptions or richer information like neural embeddings from ASR to NLU.In this paper, we study how interfaces affect joint-training for spoken language understanding.Most notably, we obtain the state-of-theart results on the publicly available 50-hr SLURP [1] dataset.We first leverage large-size pretrained ASR and NLU models that are connected by a text interface, and then jointly train both models via a sequence loss function.For scenarios where pretrained models are not utilized, the best results are obtained through a joint sequence loss training using richer neural interfaces.Finally, we show the overall diminishing impact of leveraging pretrained models with increased training data size.

Incremental learning is one paradigm to enable model building and updating at scale with streaming data. For end-to-end automatic speech recognition (ASR) tasks, the absence of human annotated labels along with the need for privacy preserving policies for model building makes it a daunting challenge. Motivated by these challenges, in this paper we use a cloud based framework for production systems to demonstrate insights from privacy preserving incremental learning for automatic speech recognition (ILASR). By privacy preserving, we mean, usage of ephemeral data which are not human annotated. This system is a step forward for production level ASR models for incremental/continual learning that offers near real-time test-bed for experimentation in the cloud for end-to-end ASR, while adhering to privacy-preserving policies. We show that the proposed system can improve the production models significantly ($3%$) over a new time period of six months even in the absence of human annotated labels with varying levels of weak supervision and large batch sizes in incremental learning. This improvement is $20%$ over test sets with new words and phrases in the new time period. We demonstrate the effectiveness of model building in a privacy-preserving incremental fashion for ASR while further exploring the utility of having an effective teacher model and use of large batch sizes.

End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the performance on rare content words often lags behind hybrid ASR systems. To address this problem, second-pass rescoring is often applied leveraging upon language modeling (LM). In this paper, we propose a second-pass system with multi-task learning, utilizing semantic targets (such as intent and slot prediction) to improve speech recognition performance. We show that our rescoring model trained with these additional tasks outperforms the baseline rescoring model, trained with only the LM task, by 1.4% on a general test and by 2.6% on a rare word test set in terms of word-error-rate relative (WERR). Our best ASR system with multi-task LM shows 4.6% WERR deduction compared with RNN Transducer only ASR baseline for rare words recognition.

Spoken language understanding (SLU) systems extract transcriptions, as well as semantics of intent or named entities from speech, and are essential components of voice activated systems. SLU models, which either directly extract semantics from audio or are composed of pipelined automatic speech recognition (ASR) and natural language understanding (NLU) models, are typically trained via differentiable cross-entropy losses, even when the relevant performance metrics of interest are word or semantic error rates. In this work, we propose non-differentiable sequence losses based on SLU metrics as a proxy for semantic error and use the REINFORCE trick to train ASR and SLU models with this loss. We show that custom sequence loss training is the state-of-the-art on open SLU datasets and leads to 6% relative improvement in both ASR and NLU performance metrics on large proprietary datasets. We also demonstrate how the semantic sequence loss training paradigm can be used to update ASR and SLU models without transcripts, using semantic feedback alone.

Comprehending the overall intent of an utterance helps a listener recognize the individual words spoken. Inspired by this fact, we perform a novel study of the impact of explicitly incorporating intent representations as additional information to improve a recurrent neural network-transducer (RNN-T) based automatic speech recognition (ASR) system. An audio-to-intent (A2I) model encodes the intent of the utterance in the form of embeddings or posteriors, and these are used as auxiliary inputs for RNN-T training and inference. Experimenting with a 50k-hour far-field English speech corpus, this study shows that when running the system in non-streaming mode, where intent representation is extracted from the entire utterance and then used to bias streaming RNN-T search from the start, it provides a 5.56% relative word error rate reduction (WERR). On the other hand, a streaming system using per-frame intent posteriors as extra inputs for the RNN-T ASR system yields a 3.33% relative WERR. A further detailed analysis of the streaming system indicates that our proposed method brings especially good gain on media-playing related intents (e.g. 9.12% relative WERR on PlayMusicIntent).

We consider the problem of spoken language understanding (SLU) of extracting natural language intents and associated slot arguments or named entities from speech that is primarily directed at voice assistants. Such a system subsumes both automatic speech recognition (ASR) as well as natural language understanding (NLU). An end-to-end joint SLU model can be built to a required specification opening up the opportunity to deploy on hardware constrained scenarios like devices enabling voice assistants to work offline, in a privacy preserving manner, whilst also reducing server costs. We first present models that extract utterance intent directly from speech without intermediate text output. We then present a compositional model, which generates the transcript using the Listen Attend Spell ASR system and then extracts interpretation using a neural NLU model. Finally, we contrast these methods to a jointly trained end-to-end joint SLU model, consisting of ASR and NLU subsystems which are connected by a neural network based interface instead of text, that produces transcripts as well as NLU interpretation. We show that the jointly trained model shows improvements to ASR incorporating semantic information from NLU and also improves NLU by exposing it to ASR confusion encoded in the hidden layer.

For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean and noisy corpus for improving automatic speech recognition (ASR) performance under multimedia noise. On top of that, we apply a logits selection method which only preserves the k highest values to prevent wrong emphasis of knowledge from the teacher and to reduce bandwidth needed for transferring data. We incorporate up to 8000 hours of untranscribed data for training and present our results on sequence trained models apart from cross entropy trained ones. The best sequence trained student model yields relative word error rate (WER) reductions of approximately 10.1%, 28.7% and 19.6% on our clean, simulated noisy and real test sets respectively comparing to a sequence trained teacher.

Neural language models (NLM) have been shown to outperform conventional n-gram language models by a substantial margin in Automatic Speech Recognition (ASR) and other tasks. There are, however, a number of challenges that need to be addressed for an NLM to be used in a practical large-scale ASR system. In this paper, we present solutions to some of the challenges, including training NLM from heterogenous corpora, limiting latency impact and handling personalized bias in the second-pass rescorer. Overall, we show that we can achieve a 6.2% relative WER reduction using neural LM in a second-pass n-best rescoring framework with a minimal increase in latency.

This paper presents a novel deep neural network (DNN) architecture with highway blocks (HWs) using a complex discrete Fourier transform (DFT) feature for keyword spotting. In our previous work, we showed that the feed-forward DNN with a time-delayed bottleneck layer (TDB-DNN) directly trained from the audio input outperformed the model with the log-mel filter bank energy feature (LFBE), given a large amount of training data [1]. However, the deeper structure of such an audio input DNN makes an optimization problem more difficult, which could easily fall in one of the local minimum solutions. In order to alleviate the problem, we propose a new HW network with a time-delayed bottleneck layer (TDB-HW). Our TDB-HW networks can learn a bottleneck feature representation through optimization based on the cross-entropy criterion without stage-wise training proposed in [1]. Moreover, we use the complex DFT feature as a method of pre-processing. Our experimental results on the real data show that the TDB-HW network with the complex DFT feature provides significantly lower miss rates for a range of false alarm rates over the LFBE DNN, yielding approximately 20 % relative improvement in the area under the curve (AUC) of the detection error tradeoff (DET) curves for keyword spotting. Furthermore, we investigate the effects of different pre-processing methods for the deep highway network.

Statistical language models (LM) play a key role in Automatic Speech Recognition (ASR) systems used by conversational agents. These ASR systems should provide a high accuracy under a variety of speaking styles, domains, vocabulary and argots. In this paper, we present a DNN-based method to adapt the LM to each user-agent interaction based on generalized contextual information, by predicting an optimal, context-dependent set of LM interpolation weights. We show that this framework for contextual adaptation provides accuracy improvements under different possible mixture LM partitions that are relevant for both (1) Goal-oriented conversational agents where it's natural to partition the data by the requested application and for (2) Non-goal oriented conversational agents where the data can be partitioned using topic labels that come from predictions of a topic classifier. We obtain a relative WER improvement of 3% with a 1-pass decoding strategy and 6% in a 2-pass decoding framework, over an unadapted model. We also show up to a 15% relative improvement in recognizing named entities which is of significant value for conversational ASR systems.

We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements. The max-pooling loss training can be further guided by initializing with a cross-entropy loss trained network. A posterior smoothing based evaluation approach is employed to measure keyword spotting performance. Our experimental results show that LSTM models trained using cross-entropy loss or max-pooling loss outperform a cross-entropy loss trained baseline feed-forward Deep Neural Network (DNN). In addition, max-pooling loss trained LSTM with randomly initialized network performs better compared to cross-entropy loss trained LSTM. Finally, the max-pooling loss trained LSTM initialized with a cross-entropy pre-trained network shows the best performance, which yields 67:6% relative reduction compared to baseline feed-forward DNN in Area Under the Curve (AUC) measure.

It has been shown that Gabor filters closely resemble the spectro-temporal response fields of neurons in the primary auditory cortex. A filter bank of 2-D Gabor filters can be applied to either the mel-spectrogram or power normalized spectrogram to obtain a set of physiologically inspired Gabor Filter Bank Features. The high dimensionality and the correlated nature of these features pose an issue for ASR. In the past, dimension reduction was performed through (1) feature selection, (2) channel selection, (3) linear dimension reduction or (4) tandem acoustic modelling. In this paper, we propose a novel solution to this issue based on channel selection and non-linear dimension reduction using Laplacian Eigenmaps. These features are concatenated with Power Normalized Cepstral Coefficients (PNCC) to evaluate if the two are complementary and provide an improvement in performance. We show a relative reduction of 12.66% in the WER compared to the PNCC baseline, when applied to the Aurora 4 database.