Logs of user queries from a search engine (such as Bing or Google) together with the links clicked provide valuable implicit feedback to improve statistical spoken language understanding (SLU) models. However, the form of natural language utterances occurring in spoken interactions with a computer differs stylistically from that of keyword search queries. In this paper, we propose a machine translation approach to learn a mapping from natural language utterances to search queries. We train statistical translation models, using task and domain independent semantically equivalent natural language and keyword search query pairs mined from the search query click logs. We then extend our previous work on enriching the existing classification feature sets for input utterance domain detection with features computed using the click distribution over a set of clicked URLs from search engine query click logs of user utterances with automatically translated queries. This approach results in significant improvements for domain detection, especially when detecting the domains of user utterances that are formulated as natural language queries and effectively complements to the earlier work using syntactic transformations.

Logs of user queries from a search engine (such as Bing or Google) together with the links clicked provide valuable implicit feedback to improve statistical spoken language understanding (SLU) models. In this work, we propose to enrich the existing classification feature set for domain detection with features computed using the click distribution over a set of clicked URLs from search query click logs (QCLs) of user utterances. Since the form of natural language utterances differs stylistically from that of keyword search queries, to be able to match natural language utterances with related search queries, we perform a syntax-based transformation of the original utterances, after filtering out domain-independent salient phrases. This approach results in significant improvements for domain detection, especially when detecting the domains of web-related user utterances.

Information retrieval in search advertising, as in other ad-hoc retrieval tasks, aims to find the most appropriate ranking of the ad documents of a corpus for a given query. In addition to ranking the ad documents, we also need to filter or threshold irrelevant ads from participating in the auction to be displayed alongside search results. In this work, we describe our experience in implementing a successful ad retrieval system for a commercial search engine based on the Language Modeling (LM) framework for retrieval. The LM demonstrates significant performance improvements over the baseline vector space model (TF-IDF) system that was in production at the time. From a modeling perspective, we propose a novel approach to incorporate query segmentation and phrases in the LM framework, discuss impact of score normalization for relevance filtering, and present preliminary results of incorporating query expansions using query rewriting techniques. From an implementation perspective, we also discuss real-time latency constraints of a production search engine and how we overcome them by adapting the WAND algorithm to work with language models. In sum, our LM formulation is considerably better in terms of accuracy metrics such as Precision-Recall (10% improvement in AUC) and nDCG (8% improvement in [email protected]) on editorial data and also demonstrates significant improvements in clicks in live user tests (0.787% improvement in Click Yield, with 8% coverage increase). Finally, we hope that this paper provides the reader with adequate insights into the challenges of building a system that serves millions of users every day.

We report on the results of the first evaluations for the BBN/LIMSI system under the new DARPA EARS program. The evaluations were carried out for conversational telephone speech (CTS) and broadcast news (BN) for three languages: English, Mandarin, and Arabic. In addition to providing system descriptions and evaluation results, the paper highlights methods that worked well across the two domains and those few that worked well on one domain but not the other. For the BN evaluations, which had to be run under 10 times real-time, we demonstrated that a joint BBN/LIMSI system with a time constraint achieved better results than either system alone.

Developing a speech application requires collecting and manually transcribing many hours of task-specific training. In recent years, unsupervised training approaches, which automatically transcribe task-dependent audio and train speech and language models using these automatic transcriptions, have reduced dependence on manual transcriptions. In this paper, we leverage our state-of-the-art speech recognition technology and use automatic transcriptions to reduce time and manual effort in developing a call routing application. Two key differentiators of our work include using different recognition strategies for unsupervised training vs. call routing, and investigating the impact of unsupervised training on call routing accuracy.

Information extraction on conversational speech presents a number of challenges. The casual speaking style and lower “fact density” typical of spontaneous conversations make named entity extraction less effective than in other domains and leads us to consider extraction of descriptive noun phrases as a more powerful generalization of named entities. We describe a system for finding semantically important noun phrases that combines our conversational speech recognizer with a probabilistic model of syntax and semantics. We present preliminary experiments on a subset of the Switchboard corpus.

This paper describes the 2000 BBN Byblos Large Vocabulary Continuous Speech Recognition (LVCSR) system. We briefly outline the training and decoding procedures used in the system, and explain in detail the new features we have added to the system in the past year. These new features include multiple adaptation stages, parallel path rescoring, and a new word confidence system. Word error rate results for all of these additions are presented for Hub-5 English test sets containing both Switchboard II and CallHome speakers. 1. Introduction The 2000 BBN Byblos LVCSR system aims for state of the art performance on decoding spontaneous, conversational telephone speech. In particular, it is explicitly designed to achieve low word error rate (WER) on the NIST sponsored Hub-5 evaluations, the test sets of which consist of equal parts of Switchboard II and CallHome conversations [1]. In the March 2000 Hub-5 evaluation, Byblos achieved a WER of 29.1%. This paper has two parts. First, we describ...

This paper describes the improvements that resulted in the 1998 Byblos large vocabulary conversational speech recognition (LVCSR) system. Salient among these improvements are: improved signal processing, improved hidden Markov model (HMM) topology, use of quinphone context, introduction of diagonal speaker adapted training (DSAT), incorporation of variance adaptation in the MLLR framework, improvements in language modeling, increase in lexicon size and combination of multiple systems. These changes resulted in about a 7% absolute reduction in word error rates on a balanced Switchboard/Callhome English test set.

Standard statistical language modeling techniques suffer from sparse-data problems in tasks where large amounts of domain-specific text are not available. In this paper, we focus on improving the estimation of domain-dependent n -gram models by the selective use of out-of-domain text data. Previous approaches for estimating language models from multi-domain data have not accounted for the characteristic variations of style and content across domains. In contrast, this work aims at differentially weighting subsets of the out-of-domain data according to style and/or content similarity to the given task, where “style" is represented by part-of-speech statistics and “content" by the particular choice of vocabulary items. In addition to n -gram estimation, the differential weights can be used for lexicon design. Recognition experiments are based on the Switchboard corpus of spontaneous conversations, with out-of-domain text drawn from the Wall Street Journal and Broadcast News corpora. The similarity weighting approach gives a 3–5% reduction in word error rate over a domain-specific n -gram language model, providing some of the largest language modeling gains reported for the Switchboard task in recent years.

Standard statistical language models use n-grams to capture local dependencies, or use dynamic modeling techniques to track dependencies within an article. In this paper, we investigate a new statistical language model that captures topic-related dependencies of words within and across sentences. First, we develop a topic-dependent, sentence-level mixture language model which takes advantage of the topic constraints in a sentence or article. Second, we introduce topic-dependent dynamic adaptation techniques in the framework of the mixture model, using n-gram caches and content word unigram caches. Experiments with the static (or unadapted) mixture model on the North American Business (NAB) task show a 21% reduction in perplexity and a 3-4% improvement in recognition accuracy over a general n-gram model, giving a larger gain than that obtained with supervised dynamic cache modeling. Further experiments on the Switchboard corpus also showed a small improvement in performance with the sentence-level mixture model. Cache modeling techniques introduced in the mixture framework contributed a further 14% reduction in perplexity and a small improvement in recognition accuracy on the NAB task for both supervised and unsupervised adaptation.

In this paper, we address the issue of deriving and using more realistic pronunciations to represent words spoken in natural conversational speech. Previous approaches include using automatic phoneme-based rule-learning techniques [1, 2, 7], linguistic transformation rules [4, 8], and phonetically hand-labelled corpus [3] to expand the number of pronunciation variants per word. While rule-based approaches have the advantage of being easily extensible to infrequent or unobserved words, they su er from the problem of over generalization. Using hand-transcribed data, one can obtain a more concise set of new pronunciations but it cannot be extended to unobserved or infrequently occuring words. In this paper, we adopt the hand-labelled corpus scheme to improve pronunciations for frequent multi and single words occurring in the training data, while using the rule-based techniques to learn pronunciation variants and their weights for the infrequent words. Furthermore, we experiment with a new approach for speaker-dependent pronunciation modeling. The newly expanded dictionaries are evaluated on the Switchboard and Callhome corpora, giving a slight reduction in word recognition error rate.

Parametric trajectory models explicitly represent the tem-poral evolution of the speech features as a Gaussian process with time-varying parameters. HMMs are a special case of such models, one in which the trajectory constraints in the speech segment are ignored by the assumption of condi-tional independence across frames within the segment. In this paper, we investigate in detail some extensions to our trajectory modeling approach aimed at improving LVCSR performance: (i) improved modeling of mixtures of trajec-tories via better initialization, (ii) modeling of context de-pendence, and (iii) improved segment boundaries by means of search. We will present results in terms of both phone classi cation and recognition accuracy on the Switchboard corpus. 1.

Standard statistical language modeling techniques suffer from sparse data problems when applied to real tasks in speech recognition, where large amounts of domain-dependent text are not available. We investigate new approaches to improve sparse application-specific language models by combining domain dependent and out-of-domain data, including a back-off scheme that effectively leads to context-dependent multiple interpolation weights, and a likelihood-based similarity weighting scheme to discriminatively use data to train a task-specific language model. Experiments with both approaches on a spontaneous speech recognition task (switchboard), lead to reduced word error rate over a domain-specific n-gram language model, giving a larger gain than that obtained with previous brute-force data combination approaches.