In the realm of spoken language understanding (SLU). numerous natural language understanding (NLU) methodologies have been adapted by supplying large language models (LLMs) with transcribed speech instead of conventional written text. In real-world scenarios, prior to input into an LLM. an automated speech recognition (ASR) system generates an output transcript hypothesis, where inherent errors can degrade subsequent SLU tasks. Here we introduce a method that utilizes the ASR system's lattice output instead of relying solely on the top hypothesis, aiming to encapsulate speech ambiguities and enhance SLU outcomes. Our in-context learning experiments, covering spoken question answering and intent classification. underline the LLM's resilience to noisy speech transcripts with the help of word confusion networks from lattices, bridging the SLU performance gap between using the top ASR hypothesis and an oracle upper bound. Additionally, we delve into the LLM's robustness to varying ASR performance conditions and scrutinize the aspects of in-context learning which prove the most influential.

Subendhu Rongali, Mukund Sridhar, Haidar Khan, Konstantine Arkoudas, Wael Hamza, Andrew McCallum. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.

We present LINGUIST, a method for generating annotated data for Intent Classification and Slot Tagging (IC+ST), via fine-tuning AlexaTM 5B, a 5-billion-parameter multilingual sequence-to-sequence (seq2seq) model, on a flexible instruction prompt. In a 10-shot novel intent setting for the SNIPS dataset, LINGUIST surpasses state-of-the-art approaches (Back-Translation and Example Extrapolation) by a wide margin, showing absolute improvement for the target intents of +1.9 points on IC Recall and +2.5 points on ST F1 Score. In the zero-shot cross-lingual setting of the mATIS++ dataset, LINGUIST out-performs a strong baseline of Machine Translation with Slot Alignment by +4.14 points absolute on ST F1 Score across 6 languages, while matching performance on IC. Finally, we verify our results on an internal large-scale multilingual dataset for conversational agent IC+ST and show significant improvements over a baseline which uses Back-Translation, Paraphrasing and Slot Catalog Resampling. To our knowledge, we are the first to demonstrate instruction fine-tuning of a large-scale seq2seq model to control the outputs of multilingual intent- and slot-labeled data generation.

Semantic parsing is an important NLP problem, particularly for voice assistants such as Alexa and Google Assistant. State-of-the-art (SOTA) semantic parsers are seq2seq architectures based on large language models that have been pretrained on vast amounts of text. To better leverage that pretraining, recent work has explored a reformulation of semantic parsing whereby the output sequences are themselves natural language sentences, but in a controlled fragment of natural language. This approach delivers strong results, particularly for few-shot semantic parsing, which is of key importance in practice and the focus of our paper. We push this line of work forward by introducing an automated methodology that delivers very significant additional improvements by utilizing modest amounts of unannotated data, which is typically easy to obtain. Our method is based on a novel synthesis of four techniques: joint training with auxiliary unsupervised tasks; constrained decoding; self-training; and paraphrasing. We show that this method delivers new SOTA few-shot performance on the Overnight dataset, particularly in very low-resource settings, and very compelling few-shot results on a new semantic parsing dataset.

We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system. Though we train using 70% spoken-form data, our teacher models perform comparably to XLM-R and mT5 when evaluated on the written-form Cross-lingual Natural Language Inference (XNLI) corpus. We perform a second stage of pretraining on our teacher models using in-domain data from our system, improving error rates by 3.86% relative for intent classification and 7.01% relative for slot filling. We find that even a 170M-parameter model distilled from our Stage 2 teacher model has 2.88% better intent classification and 7.69% better slot filling error rates when compared to the 2.3B-parameter teacher trained only on public data (Stage 1), emphasizing the importance of in-domain data for pretraining. When evaluated offline using labeled NLU data, our 17M-parameter Stage 2 distilled model outperforms both XLM-R Base (85M params) and DistillBERT (42M params) by 4.23% to 6.14%, respectively. Finally, we present results from a full virtual assistant experimentation platform, where we find that models trained using our pretraining and distillation pipeline outperform models distilled from 85M-parameter teachers by 3.74%-4.91% on an automatic measurement of full-system user dissatisfaction.

Voice Assistants such as Alexa, Siri, and Google Assistant typically use a two-stage Spoken Language Understanding pipeline; first, an Automatic Speech Recognition (ASR) component to process customer speech and generate text transcriptions, followed by a Natural Language Understanding (NLU) component to map transcriptions to an actionable hypothesis. An end-to-end (E2E) system that goes directly from speech to a hypothesis is a more attractive option. These systems were shown to be smaller, faster, and better optimized. However, they require massive amounts of end-to-end training data and in addition, don't take advantage of the already available ASR and NLU training data. In this work, we propose an E2E system that is designed to jointly train on multiple speech-to-text tasks, such as ASR (speech-transcription) and SLU (speech-hypothesis), and text-to-text tasks, such as NLU (text-hypothesis). We call this the Audio-Text All-Task (AT-AT) Model and we show that it beats the performance of E2E models trained on individual tasks, especially ones trained on limited data. We show this result on an internal music dataset and two public datasets, FluentSpeech and SNIPS Audio, where we achieve state-of-the-art results. Since our model can process both speech and text input sequences and learn to predict a target sequence, it also allows us to do zero-shot E2E SLU by training on only text-hypothesis data (without any speech) from a new domain. We evaluate this ability of our model on the Facebook TOP dataset and set a new benchmark for zeroshot E2E performance. We release the audio data collected for the TOP dataset for future research.

Shuyang Li, Jin Cao, Mukund Sridhar, Henghui Zhu, Shang-Wen Li, Wael Hamza, Julian McAuley. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

Current spoken language understanding systems heavily rely on the best hypothesis (ASR 1-best) generated by automatic speech recognition, which is used as the input for downstream models such as natural language understanding (NLU) modules. However, the potential errors and misrecognition in ASR 1-best raise challenges to NLU. It is usually difficult for NLU models to recover from ASR errors without additional signals, which leads to suboptimal SLU performance. This paper proposes a fusion network to jointly consider ASR n-best hypotheses for enhanced robustness to ASR errors. Our experiments on Alexa data show that our model achieved 21.71% error reduction compared to baseline trained on transcription for domain classification.

Semantic parsing is one of the key components of natural language understanding systems.A successful parse transforms an input utterance to an action that is easily understood by the system.Many algorithms have been proposed to solve this problem, from conventional rulebased or statistical slot-filling systems to shiftreduce based neural parsers.For complex parsing tasks, the state-of-the-art method is based on autoregressive sequence to sequence models to generate the parse directly.This model is slow at inference time, generating parses in O(n) decoding steps (n is the length of the target sequence).In addition, we demonstrate that this method performs poorly in zero-shot cross-lingual transfer learning settings.In this paper, we propose a non-autoregressive parser which is based on the insertion transformer to overcome these two issues.Our approach 1) speeds up decoding by 3x while outperforming the autoregressive model and 2) significantly improves cross-lingual transfer in the low-resource setting by 37% compared to autoregressive baseline.We test our approach on three well-known monolingual datasets: ATIS, SNIPS and TOP.For cross lingual semantic parsing, we use the MultiATIS++ and the multilingual TOP datasets.

Neural models have yielded state-of-the-art results in deciphering spoken language understanding (SLU) problems; however, these models require a significant amount of domain-specific labeled examples for training, which is prohibitively expensive. While pre-trained language models like BERT have been shown to capture a massive amount of knowledge by learning from unlabeled corpora and solve SLU using fewer labeled examples for adaption, the encoding of knowledge is implicit and agnostic to downstream tasks. Such encoding results in model inefficiencies in parameter usage: an entirely new model is required for every domain. To address these challenges, we introduce a novel SLU framework, comprising a conversational language modeling (CLM) pre-training task and a light encoder architecture. The CLM pre-training enables networks to capture the representation of the language in conversation style with the presence of ASR errors. The light encoder architecture separates the shared pre-trained networks from the mappings of generally encoded knowledge to specific domains of SLU, allowing for the domain adaptation to be performed solely at the light encoder and thus increasing efficiency. With the framework, we match the performance of state-of-the-art SLU results on Alexa internal datasets and on two public ones (ATIS, SNIPS), adding only 4.4% parameters per task.

Virtual assistants such as Amazon Alexa, Apple Siri, and Google Assistant often rely on a semantic parsing component to understand which action(s) to execute for an utterance spoken by its users. Traditionally, rule-based or statistical slot-filling systems have been used to parse “simple” queries; that is, queries that contain a single action and can be decomposed into a set of non-overlapping entities. More recently, shift-reduce parsers have been proposed to process more complex utterances. These methods, while powerful, impose specific limitations on the type of queries that can be parsed; namely, they require a query to be representable as a parse tree.

A major challenge in Entity Linking (EL) is making effective use of contextual information to disambiguate mentions to Wikipedia that might refer to different entities in different contexts. The problem exacerbates with cross-lingual EL which involves linking mentions written in non-English documents to entries in the English Wikipedia: to compare textual clues across languages we need to compute similarity between textual fragments across languages. In this paper, we propose a neural EL model that trains fine-grained similarities and dissimilarities between the query and candidate document from multiple perspectives, combined with convolution and tensor networks. Further, we show that this English-trained system can be applied, in zero-shot learning, to other languages by making surprisingly effective use of multi-lingual embeddings. The proposed system has strong empirical evidence yielding state-of-the-art results in English as well as cross-lingual: Spanish and Chinese TAC 2015 datasets.

Natural language sentence matching is a fundamental technology for a variety of tasks. Previous approaches either match sentences from a single direction or only apply single granular (word-by-word or sentence-by-sentence) matching. In this work, we propose a bilateral multi-perspective matching (BiMPM) model. Given two sentences P and Q, our model first encodes them with a BiLSTM encoder. Next, we match the two encoded sentences in two directions P against Q and P against Q. In each matching direction, each time step of one sentence is matched against all time-steps of the other sentence from multiple perspectives. Then, another BiLSTM layer is utilized to aggregate the matching results into a fix-length matching vector. Finally, based on the matching vector, a decision is made through a fully connected layer. We evaluate our model on three tasks: paraphrase identification, natural language inference and answer sentence selection. Experimental results on standard benchmark datasets show that our model achieves the state-of-the-art performance on all tasks.

Expressive text-to-speech (TTS) synthesis should contribute to the pleasantness, intelligibility, and speed of speech-based human-machine interactions which use TTS. We describe a TTS engine which can be directed, via text markup, to use a variety of expressive styles, here, questioning, contrastive emphasis, and conveying good and bad news. Differences in these styles lead us to investigate two approaches for expressive TTS, a "corpus-driven" and a "prosodic-phonology" approach. Each speaker records 11 h (excluding silences) of "neutral" sentences. In the corpus-driven approach, the speaker also records 1-h corpora in each expressive style; these segments are tagged by style for use during search, and decision trees for determining f0contours and timing are trained separately for each of the neutral and expressive corpora. In the prosodic-phonology approach, rules translating certain expressive markup elements to tones and break indices (ToBI) are manually determined, and the ToBI elements are used in single f0and duration trees for all expressions. Tests show that listeners identify synthesis in particular styles ranging from 70% correctly for "conveying bad news" to 85% for "yes-no questions". Further improvements are demonstrated through the use of speaker-pooled f0and duration models

Text-to-speech systems have dramatically improved in recent years through the use of corpus-based concatenative approaches, and we are beginning to see an interest in endowing them with the ability to handle more than the native language for which they have been developed. In this paper we present ongoing work at IBM in text-to-speech systems that can produce high-quality synthesis in more than one language. We illustrate the discussion with a case study in which two systems, originally developed to support English and Mandarin respectively, have been extended to support each other’s languages. We describe the challenges faced when adapting one system to a different target language, propose adaptation solutions, and present the results of perceptual tests carried out to evaluate how the approaches compare with the performance of the native systems.

In this paper, we compare two methods of building a concatenative speech synthesis system from the relatively small, “Blizzard Challenge ” speech databases. In the first method we build a system directly from the Blizzard databases using the IBM Concatenetative Speech Synthesis System originally designed for very large speech databases. In the second method, a larger database is used to build the synthesis system and the output is “morphed ” to match the speakers in the Blizzard databases. The second method outperformed the first while maintaining the identity of the Blizzard target speakers. 1.

In this paper, methods for reconciling pronunciation differences between a rule-based front-end and the pronunciations observed in a database of recorded speech are presented. The methods are applied to the IBM Expressive Speech Synthesis System [1] for both unrestricted and limited-domain text-to-speech synthesis. One method is based on constructing a multiple pronunciation lattice for the given sentence and scoring it using word and phoneme n-gram statistics computed from the target speaker’s database. A second method consists of storing observed pronunciations and introducing them as alternates in the search. We compare the strengths and weaknesses of these two methods. Results show that improvements are achieved in both limited and unrestricted domains, with the largest gains coming in the limited-domain case.

This paper introduces the IBM Expressive Speech Synthesis system. We describe recent work in improving the quality of our baseline text-to-speech system as well as extending our capabilities to generate expressive synthetic speech. We present results showing improved base quality, especially for sentences drawn from a limited domain. We also demonstrate our ability to convey good news and bad news, produce contrastive emphasis, and ask a question appropriately. In order to facilitate access to the expressive capabilities, we use some of our proposed extensions to the Speech Synthesis Markup Language (SSML). 1.

In this paper we describe the current status of the trainable text-to-speech system at IBM. Recent algorithmic and database changes to the system have led to significant gains in the output quality. On the algorithms side, we have introduced statistical models for predicting pitch and duration targets which replace the rule-based target generation previously employed. Additionally, we have changed the cost function and the search strategy, introduced a post-search pitch smoothing algorithm, and improved our method of preselection. Through the combined data and algorithmic contributions, we have been able to significantly improve (p < 0.0001) the mean opinion score (MOS) of our female voice, from 3.68 to 4.85 when heard over loudspeakers and to 5.42 when heard over the telephone (seven point scale).

Modeling phonetic context is one of the key points to get natural sounding in concatenativc speech synthesis. In this paper, a new quantitative method to model context is proposed. In the proposed method, the context is measured as the distance between leafs of the top-down likelihood-based decision trees that have been grown during the construction of acoustic inventory. Unlike other context modeling methods, this method allows the unit selection algorithm to borrow unit occurrences from other contexts when their context distances are close. This is done by incorporating the measured distance as an element in the unit selection cost function. The motivation behind this method is that it reduces the required speech modification by using better unit occurrences from near context. This method also makes it easy to use long synthesis units, e.g. syllables or words, in the same unit selection framework.