My Research Page

My main area of research is computational linguistics, specifically the relationship between intonation and discourse. My current interests include emotional speech (including deceptive and charismatic speech); intonation variation in spoken dialogue systems; speech synthesis; speech search and summarization over large corpora of broadcast news and voicemail; and interfaces to speech corpora. Below are some of my papers. A complete list of publications can be found in my resume; if you have trouble finding any papers, please send me email. Slides from a tutorial with a bibliography are also available for download.  Also, I have written several general surveys of work on intonational meaning and text-to-speech synthesis, including "Communication and Prosody" in Speech Communication 36 (2002), an article in the Handbook of Pragmatics, "Pragmatics and Intonation," (2003), and a section of the second edition of the Encyclopedia of Language and Linguistics on “Speech Synthesis, Prosody” (final draft). See for a fuller listing of publications from the Speech Lab. For a list of current and past collaborators on Columbia projects, and a fuller description of these projects, please see our lab projects page.

Past and Present Research Projects

Emotional Speech, Deceptive Speech, and Charismatic Speech

Jennifer Venditti, Jackson Liscombe, Agustin Gravano, and I have been looking at various methods of eliciting both subjective and objective judgments and of correlating judgments of single tokens on multiple emotion scale -- i.e., if subjects rate a token high for frustration, what other emotional states do they also rate it high for -- or low ("Classifying Subjective Ratings of Emotional Speech," Eurospeech 2003). We conducted some eye-tracking experiments which allow us to compare subjective judgments to more objective cues to the decision process. We are also working with colleagues at the University of Pittsburgh to study speaker state student speech in a tutorial system for emotional states such as anger, frustration, confidence and uncertainty (“Detecting Certainness in Spoken Tutorial Dialogues,” INTERSPEECH 2005 – Eurospeech). Frank Enos, Stefan Benus, and I are also working with colleagues at SRI/ICSI and the University of Colorado on automatic methods of distinguishing deceptive from non-deceptive speech (“Distinguishing Deceptive from Non-Deceptive Speech,” INTERSPEECH 2005 – Eurospeech).  And Andrew Rosenberg and I are working on the acoustic, prosodic, and lexical cues to charismatic speech in American English (“Acoustic/Prosodic and Lexical Correlates of Charismatic Speech”, INTERSPEECH 2005 – Eurospeech). Fadi Biadsy has now joined our effort to extend our research to Palestinian Arabic.

Speech Summarization, Distillation

With Sameer Maskey, Andrew Rosenberg, Fadi Biadsy, and Martin Jansche, I have been working on speech summarization. We are exploring new techniques which take advantage of prosodic and acoustic information, in addition to lexical cues and structural cues in news broadcasts to 'gist' a broadcast “Comparing Lexical, Acoustic/Prosodic, Structural and Discourse Features for Speech Summarization,” INTERSPEECH 2005 – Eurospeech; and “Summarizing Speech without Text Using Hidden Markov Models,” HLT/NAACL 2006). We have also looked at the segmentation of news broadcasts into stories (“Story Segmentation of Broadcast News in English, Mandarin and Arabic” HLT/NAACL 2006), the determination of speaker roles (e.g. anchor, reporter, interviewee ) (See R. Barzilay et al., " Identification of Speaker Role in Radio Broadcasts", AAAI 2000 for earlier work.), and the extraction of soundbites from broadcasts (spoken ‘quotes’ included in a show) and identification of their speaker.

Spoken Dialogue Systems

The Columbia Games Corpus

Agus Gravano, Stefan Benus, and I have been collecting and analyzing a large corpus of spontaneous dialogues, produced by subjects playing a computer game we created. We collected this data to test several theories of the way speakers produce ‘given’ (as opposed to ‘new’) information. We are currently labeling this corpus in ToBI and have identified different turn-taking behaviors, cue phrases, questions (identified as to form and function) and other aspects of the corpus. This is joint work with Gregory Ward and colleagues at Northwestern University.

Misrecognitions, Corrections, and Error Awareness

Diane Litman, Marc Swerts and I have been working on the prosodic consequences of recognition errors in Spoken Dialogue Systems. We are studying whether prosodic features of user utterances can tell us a) whether a speech recognition error has occurred, as a user reacts to it (e.g. System: "Did you say you want to go to Baltimore?" User: "NO!"), or, b) whether a user is in fact correcting such a recognition error (e.g. User: "I want to go to BOSTON!". We have already found that prosodic features predict recognition errors directly with considerable accuracy in the TOOT train information corpus dialogues. Using machine learning techniques, we have found that, in combination with information already available to the recognizer, such as acoustic confidence scores, grammar, and recognized string, prosodic information can distinguish speaker turns that are misrecognized far better than traditional methods for ASR rejection using acoustic confidence scores alone. See Julia Hirschberg, Diane Litman and Marc Swerts, “Prosodic and Other Cues to Speech Recognition Failures,” Speech Communication 2004. We have also studied user corrections of system errors in the TOOT corpus, finding also significant prosodic differences between corrections and non-corrections that can be used to predict when a user is correcting the system with some success; in addition we find interesting and useful correlations between system strategies and types of user corrections, as well as evidence for what types of corrections are more successful (see "Corrections in Spoken Dialogue Systems", presented at ICSLP-00 and "Identifying User Corrections Automatically in Spoken Dialogue Systems"), presented at NAACL-01.

Audio Browsing and Retrieval

Work on our SCAN (Spoken Content-Based Audio Navigation) browsing and retrieval system is summarized in John Choi et al., "Spoken Content-Based Audio Navigation (SCAN)," ICPhS-99. This project combines ASR and IR technology to enable search of large audio databases, such as broadcast news archives or voicemail. It started life as `AudioGrep'. Current collaborators include Steve Abney, Brian Amento, Michiel Bacchiani, Phil Isenhour, Diane Litman, Larry Stead, and Steve Whittaker. My particular interests lie in the use of acoustic information to segment audio (Julia Hirschberg and Christine Nakatani, "Acoustic Indicators of Topic Segmentation," ICSLP-98) and the study of how people browse and search audio databases such as broadcast news collections (Steve Whittaker et al., "SCAN: Designing and Evaluating User Interfaces to Support Retrieval from Speech Archives ", SIGIR-99) and voicemail (Steve Whittaker, Julia Hirschberg and Christine Nakatani, "Play it again: a study of the factors underlying speech browsing behavior," and Steve Whittaker, Julia Hirschberg and Christine Nakatani, "All talk and all action: strategies for managing voicemail messages," both presented at CHI-98). We have also studied how differences in ASR accuracy (comparing 100%, 84%, 69%, 50% accuracy transcripts) affect users' ability to perform tasks, finding effects for transcript accuracy on time to solution, amount of speech played, likelihood of subjects abandoning transcript, and various subjective measures; however, our results hold only when we collapse our four categories into two; i.e., there are no differences between perfect and 84% accurate transcripts or between 69% and 50% accurate ones (Litza Stark, Steve Whittaker, and Julia Hirschberg, "ASR Satisficing: The effects of ASR accuracy on speech retrieval", ICSLP-00). Currently, in a new voicemail application, SCANMail, now in friendly trial, we have ported SCAN technology to the voicemail domain: users are able to browse and retrieve their voicemail by content. See J. Hirschberg et al., "SCANMail: Browsing and Searching Speech Data by Content Domain" and A. Rosenberg et al., "Caller Identification for the SCANMail Voicemail Browser" (both presented at Eurospeech 2001). Meredith Ringel and I have also worked on ranking voicemail messages as to urgency and distinguishing personal from business methods, using machine learning techniques ("Automated Message Prioritization: Making Voicemail Retrieval More Efficient", presented at CHI 2002).

Intonation and Discourse Structure

Some results of a long collaboration with Barbara Grosz and Christine Nakatani on the intonational correlates of discourse structure in read and spontaneous speech is described in " A Prosodic Analysis of Discourse Segments in Direction-Giving Monologues ," (ACL-96). The BDC corpus (with ToBI labels) is available here.  Results of earlier studies of read speech are described in "Some Intonational Characteristics of Discourse Structure ," (a reformatted version of ICSLP-92).

Intonational Disambiguation

Empirical studies comparing the way native speakers of different languages employ intonational variation to disambiguate are described in Julia Hirschberg and Cinzia Avesani, "The Role of Prosody in Disambiguating Potentially Ambiguous Utterances in English and Italian," ESCA Tutorial and Research Workshop on Intonation, Athens, 1997.

Disfluencies in Spontaneous Speech

Christine Nakatani and Julia Hirschberg, "A Corpus-based study of repair cues in spontaneous speech," JASA, 1994, describes studies of the acoustic/prosodic characteristics of self-repairs.

Cue Phrases

Work on cue phrases, or discourse markers, is described in Julia Hirschberg and Diane Litman, "Empirical Studies on the Disambiguation of Cue Phrases"," Computational Linguistics, 1992; some figures are missing in this version). More recently Agus Gravano, Stefan Benus and I have been looking at cue phrase production in the Games corpus (see above).

Intonational Variation in Synthetic Speech

I collaborated most recently on two projects in concept-to-speech generation (generating speech from an abstract representation of the concepts to be conveyed). One, with Shimei Pan and Kathy McKeown of Columbia University, seeks to assign prosody appropriately for a multimodal medical application, MAGIC. Some results are documented in Shimei Pan, Kathy McKeown and Julia Hirschberg, "Semantic Abnormality and its Realization in Spoken Language," Proceedings of Eurospeech 2001, Aalborg. The other, with Srinivas Bangalore, Owen Rambow, and Marilyn Walker (AT&T Labs -- Research) involves prosodic assignment in the DARPA Communicator travel information domain. Some results appear in Julia Hirschberg and Owen Rambow, "Learning Prosodic Features using a Tree Representation," Proceedings of Eurospeech 2001, Aalborg. Much of my work has focussed on text-to-speech (generating speech from input text). The papers below describe the application of experimental results in intonational variation to text-to-speech; procedures described below are used to assign phrase boundaries and pitch accent in the AT&T Text-to-Speech System.

         Assigning Intonational Phrase Boundaries

Philipp Koehn, Steven Abney, Julia Hirschberg, and Michael Collins, Improving Intonational Phrasing with Syntactic Information", to appear in ICASSP-00. Julia Hirschberg and Pilar Prieto, "Training intonational phrasing rules automatically for English and Spanish Text-to-Speech", Speech Communication, 1996. Michelle Wang and Julia Hirschberg, " Automatic Classification of Intonational Phrase Boundaries," Computer Speech and Language, 1992.

Assigning Intonational Prominences

See Julia Hirschberg, "Pitch Accent in Context: Predicting Intonational Prominence from Text," Artificial Intelligence, 1993.

Controlling Intonational Variation in TTS

A paper describing command line control of escape sequences describes their use in AT&T's TTS system.

Labeling Conventions and Labeled Corpora

I have been an active participant in the development of the ToBI Labeling Standard for the prosodic labeling of Standard American English (see the ToBI conventions for a quick overview). . This standard was developed by a number of researchers from industry and academia and has been extended for other dialects of English and for other languages, including Italian, German, Spanish, Japanese and more. Interlabeler reliability ratings (see John Pitrelli, Mary Beckman, and Julia Hirschberg,``Evaluation of Prosodic Transcription Labeling Reliability in the ToBI Framework,'' Proceedings of the Third International Conference on Spoken Language Processing, Yokohama, September, 1994, pp. 123-126) are quite good and there are tools and training materials available with pdf and html versions and praat files there. There is also a Wavesurfer version and another Praat version with cardinal examples done by Agus Gravano and available from the Columbia ToBI site. Andrew Rosenberg and I have been working recently on the identification of ToBI labels using acoustic features in AuToBI with promising results which we hope to report soon.