Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systems

Training an end-to-end (E2E) neural network speech-to-intent (S2I) system that directly extracts intents from speech requires large amounts of intent-labeled speech data, which is time consuming and expensive to collect. Initializing the S2I model with an ASR model trained on copious speech data can alleviate data sparsity. In this paper, we attempt to leverage NLU text resources. We implemented a CTC-based S2I system that matches the performance of a state-of-the-art, traditional cascaded SLU system. We performed controlled experiments with varying amounts of speech and text training data. When only a tenth of the original data is available, intent classification accuracy degrades by 7.6% absolute. Assuming we have additional text-to-intent data (without speech) available, we investigated two techniques to improve the S2I system: (1) transfer learning, in which acoustic embeddings for intent classification are tied to fine-tuned BERT text embeddings; and (2) data augmentation, in which the text-to-intent data is converted into speech-to-intent data using a multi-speaker text-to-speech system. The proposed approaches recover 80% of performance lost due to using limited intent-labeled speech.

End-to-End Spoken Language Understanding Without Full Transcripts

An essential component of spoken language understanding (SLU) is slot filling: representing the meaning of a spoken utterance using semantic entity labels. In this paper, we develop end-to-end (E2E) spoken language understanding systems that directly convert speech input to semantic entities and investigate if these E2E SLU models can be trained solely on semantic entity annotations without word-for-word transcripts. Training such models is very useful as they can drastically reduce the cost of data collection. We created two types of such speech-to-entities models, a CTC model and an attention-based encoder-decoder model, by adapting models trained originally for speech recognition. Given that our experiments involve speech input, these systems need to recognize both the entity label and words representing the entity value correctly. For our speech-to-entities experiments on the ATIS corpus, both the CTC and attention models showed impressive ability to skip non-entity words: there was little degradation when trained on just entities versus full transcripts. We also explored the scenario where the entities are in an order not necessarily related to spoken order in the utterance. With its ability to do re-ordering, the attention model did remarkably well, achieving only about 2% degradation in speech-to-bag-of-entities F1 score.

AVLnet: Learning Audio-Visual Language Representations from Instructional Videos

Current methods for learning visually grounded language from videos often rely on time-consuming and expensive data collection, such as human annotated textual summaries or machine generated automatic speech recognition transcripts. In this work, we introduce Audio-Video Language Network (AVLnet), a self-supervised network that learns a shared audio-visual embedding space directly from raw video inputs. We circumvent the need for annotation and instead learn audio-visual language representations directly from randomly segmented video clips and their raw audio waveforms. We train AVLnet on publicly available instructional videos and evaluate our model on video clip and language retrieval tasks on three video datasets. Our proposed model outperforms several state-of-the-art text-video baselines by up to 11.8% in a video clip retrieval task, despite operating on the raw audio instead of manually annotated text captions. Further, we show AVLnet is capable of integrating textual information, increasing its modularity and improving performance by up to 20.3% on the video clip retrieval task. Finally, we perform analysis of AVLnet's learned representations, showing our model has learned to relate visual objects with salient words and natural sounds.

English Broadcast News Speech Recognition by Humans and Machines

With recent advances in deep learning, considerable attention has been given to achieving automatic speech recognition performance close to human performance on tasks like conversational telephone speech (CTS) recognition. In this paper we evaluate the usefulness of these proposed techniques on broadcast news (BN), a similar challenging task. We also perform a set of recognition measurements to understand how close the achieved automatic speech recognition results are to human performance on this task. On two publicly available BN test sets, DEV04F and RT04, our speech recognition system using LSTM and residual network based acoustic models with a combination of n-gram and neural network language models performs at 6.5% and 5.9% word error rate. By achieving new performance milestones on these test sets, our experiments show that techniques developed on other related tasks, like CTS, can be transferred to achieve similar performance. In contrast, the best measured human recognition performance on these test sets is much lower, at 3.6% and 2.8% respectively, indicating that there is still room for new techniques and improvements in this space, to reach human performance levels.

Understanding Unequal Gender Classification Accuracy from Face Images

Recent work shows unequal performance of commercial face classification services in the gender classification task across intersectional groups defined by skin type and gender. Accuracy on dark-skinned females is significantly worse than on any other group. In this paper, we conduct several analyses to try to uncover the reason for this gap. The main finding, perhaps surprisingly, is that skin type is not the driver. This conclusion is reached via stability experiments that vary an image's skin type via color-theoretic methods, namely luminance mode-shift and optimal transport. A second suspect, hair length, is also shown not to be the driver via experiments on face images cropped to exclude the hair. Finally, using contrastive post-hoc explanation techniques for neural networks, we bring forth evidence suggesting that differences in lip, eye and cheek structure across ethnicity lead to the differences. Further, lip and eye makeup are seen as strong predictors for a female face, which is a troubling propagation of a gender stereotype.

SimplerVoice: A Key Message & Visual Description Generator System for Illiteracy

We introduce SimplerVoice: a key message and visual description generator system to help low-literate adults navigate the information-dense world with confidence, on their own. SimplerVoice can automatically generate sensible sentences describing an unknown object, extract semantic meanings of the object usage in the form of a query string, then, represent the string as multiple types of visual guidance (pictures, pictographs, etc.). We demonstrate SimplerVoice system in a case study of generating grocery products' manuals through a mobile application. To evaluate, we conducted a user study on SimplerVoice's generated description in comparison to the information interpreted by users from other methods: the original product package and search engines' top result, in which SimplerVoice achieved the highest performance score: 4.82 on 5-point mean opinion score scale. Our result shows that SimplerVoice is able to provide low-literate end-users with simple yet informative components to help them understand how to use the grocery products, and that the system may potentially provide benefits in other real-world use cases

A Recorded Debating Dataset

This paper describes an English audio and textual dataset of debating speeches, a unique resource for the growing research field of computational argumentation and debating technologies. We detail the process of speech recording by professional debaters, the transcription of the speeches with an Automatic Speech Recognition (ASR) system, their consequent automatic processing to produce a text that is more "NLP-friendly", and in parallel -- the manual transcription of the speeches in order to produce gold-standard "reference" transcripts. We release 60 speeches on various controversial topics, each in five formats corresponding to the different stages in the production of the data. The intention is to allow utilizing this resource for multiple research purposes, be it the addition of in-domain training data for a debate-specific ASR system, or applying argumentation mining on either noisy or clean debate transcripts. We intend to make further releases of this data in the future.

Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition

The performance of automatic speech recognition systems degrades with increasing mismatch between the training and testing scenarios. Differences in speaker accents are a significant source of such mismatch. The traditional approach to deal with multiple accents involves pooling data from several accents during training and building a single model in multi-task fashion, where tasks correspond to individual accents. In this paper, we explore an alternate model where we jointly learn an accent classifier and a multi-task acoustic model. Experiments on the American English Wall Street Journal and British English Cambridge corpora demonstrate that our joint model outperforms the strong multi-task acoustic model baseline. We obtain a 5.94% relative improvement in word error rate on British English, and 9.47% relative improvement on American English. This illustrates that jointly modeling with accent information improves acoustic model performance.

English Conversational Telephone Speech Recognition by Humans and Machines

One of the most difficult speech recognition tasks is accurate recognition of human to human communication. Advances in deep learning over the last few years have produced major speech recognition improvements on the representative Switchboard conversational corpus. Word error rates that just a few years ago were 14% have dropped to 8.0%, then 6.6% and most recently 5.8%, and are now believed to be within striking range of human performance. This then raises two issues - what IS human performance, and how far down can we still drive speech recognition error rates? A recent paper by Microsoft suggests that we have already achieved human performance. In trying to verify this statement, we performed an independent set of human performance measurements on two conversational tasks and found that human performance may be considerably better than what was earlier reported, giving the community a significantly harder goal to achieve. We also report on our own efforts in this area, presenting a set of acoustic and language modeling techniques that lowered the word error rate of our own English conversational telephone LVCSR system to the level of 5.5%/10.3% on the Switchboard/CallHome subsets of the Hub5 2000 evaluation, which - at least at the writing of this paper - is a new performance milestone (albeit not at what we measure to be human performance!). On the acoustic side, we use a score fusion of three models: one LSTM with multiple feature inputs, a second LSTM trained with speaker-adversarial multi-task learning and a third residual net (ResNet) with 25 convolutional layers and time-dilated convolutions. On the language modeling side, we use word and character LSTMs and convolutional WaveNet-style language models.

Invariant Representations for Noisy Speech Recognition

Modern automatic speech recognition (ASR) systems need to be robust under acoustic variability arising from environmental, speaker, channel, and recording conditions. Ensuring such robustness to variability is a challenge in modern day neural network-based ASR systems, especially when all types of variability are not seen during training. We attempt to address this problem by encouraging the neural network acoustic model to learn invariant feature representations. We use ideas from recent research on image generation using Generative Adversarial Networks and domain adaptation ideas extending adversarial gradient-based training. A recent work from Ganin et al. proposes to use adversarial training for image domain adaptation by using an intermediate representation from the main target classification network to deteriorate the domain classifier performance through a separate neural network. Our work focuses on investigating neural architectures which produce representations invariant to noise conditions for ASR. We evaluate the proposed architecture on the Aurora-4 task, a popular benchmark for noise robust ASR. We show that our method generalizes better than the standard multi-condition training especially when only a few noise categories are seen during training.