Departments View all

Publication History View all

  • [Show abstract] [Hide abstract]
    ABSTRACT: We present our approach to unsupervised training of speech recognizers. Our approach iteratively adjusts sound units that are optimized for the acoustic domain of interest. We thus enable the use of speech recognizers for applications in speech domains where transcriptions do not exist. The resulting recognizer is a state-of-the-art recognizer on the optimized units. Specifically we propose building HMM-based speech recognizers without transcribed data by formulating the HMM training as an optimization over both the parameter and transcription sequence space. Audio is then transcribed into these self-organizing units (SOUs). We describe how SOU training can be easily implemented using existing HMM recognition tools. We tested the effectiveness of SOUs on the task of topic classification on the Switchboard and Fisher corpora. On the Switchboard corpus, the unsupervised HMM-based SOU recognizer, initialized with a segmental tokenizer, performed competitively with an HMM-based phoneme recognizer trained with 1 h of transcribed data, and outperformed the Brno University of Technology (BUT) Hungarian phoneme recognizer (Schwartz et al., 2004). We also report improvements, including the use of context dependent acoustic models and lattice-based features, that together reduce the topic verification equal error rate from 12% to 7%. In addition to discussing the effectiveness of the SOU approach, we describe how we analyzed some selected SOU n-grams and found that they were highly correlated with keywords, demonstrating the ability of the SOU technology to discover topic relevant keywords.
    Computer Speech & Language 01/2014; 28(1):210–223.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we present a speech-to-speech (S2S) translation system called the BBN TransTalk that enables two-way communication between speakers of English and speakers who do not understand or speak English. The BBN TransTalk has been configured for several languages including Iraqi Arabic, Pashto, Dari, Farsi, Malay, Indonesian, and Levantine Arabic. We describe the key components of our system: automatic speech recognition (ASR), machine translation (MT), text-to-speech (TTS), dialog manager, and the user interface (UI). In addition, we present novel techniques for overcoming specific challenges in developing high-performing S2S systems. For ASR, we present techniques for dealing with lack of pronunciation and linguistic resources and effective modeling of ambiguity in pronunciations of words in these languages. For MT, we describe techniques for dealing with data sparsity as well as modeling context. We also present and compare different user confirmation techniques for detecting errors that can cause the dialog to drift or stall.
    Computer Speech & Language 02/2013; 27(2):475–491.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a workflow for the design and production of biological networks from high-level program specifications. The workflow is based on a sequence of intermediate models that incrementally translate high-level specifications into DNA samples that implement them. We identify algorithms for translating between adjacent models and implement them as a set of software tools, organized into a four-stage toolchain: Specification, Compilation, Part Assignment, and Assembly. The specification stage begins with a Boolean logic computation specified in the Proto programming language. The compilation stage uses a library of network motifs and cellular platforms, also specified in Proto, to transform the program into an optimized Abstract Genetic Regulatory Network (AGRN) that implements the programmed behavior. The part assignment stage assigns DNA parts to the AGRN, drawing the parts from a database for the target cellular platform, to create a DNA sequence implementing the AGRN. Finally, the assembly stage computes an optimized assembly plan to create the DNA sequence from available part samples, yielding a protocol for producing a sample of engineered plasmids with robotics assistance. Our workflow is the first to automate the production of biological networks from a high-level program specification. Furthermore, the workflow's modular design allows the same program to be realized on different cellular platforms simply by swapping workflow configurations. We validated our workflow by specifying a small-molecule sensor-reporter program and verifying the resulting plasmids in both HEK 293 mammalian cells and in E. coli bacterial cells.
    ACS Synthetic Biology 08/2012; 1(8):317-31.

Information

  • Address
    Cambridge, United States
Information provided on this web page is aggregated encyclopedic and bibliographical information relating to the named institution. Information provided is not approved by the institution itself. The institution’s logo (and/or other graphical identification, such as a coat of arms) is used only to identify the institution in a nominal way. Under certain jurisdictions it may be property of the institution.

85 Members View all

View all

Top publications last week by downloads

 
22 Downloads
 
Cyber Journals: Journal of Selected Areas in Telecommunications. 04/2011;
19 Downloads

Top Collaborating Institutions

Collaborations

This map visualizes which other institutions researchers from Raytheon BBN Technologies have collaborated with.

Rg score distribution

See how the RG Scores of researchers from Raytheon BBN Technologies are distributed.