For Class

Language Modeling Toolkits

OpenEars
Brandeis is in the Apple iOS Univeristy Developer Program , which provides the Apple Developer Library There is a lot of informatin available from development videos to sample code. Let me know if you're going to do this, since I need to give you log ins and register your devices
iSpeech
WebSpeech API forChrome. IntroThe new JavaScript Web Speech API makes it easy to add speech recognition to your web pages. This API allows fine control and flexibility over the speech recognition capabilities in Chrome version 25 and later.
Speech Mashup Guide More on the Mashup from Thomas:

As far as HTML-based PC/Mac clients are concerned, the same Java applets as before can still be used. Oracle is tightening the signing requirements on applets, so running our applets now requires installing a certificate on the client side, but otherwise it still works as before.
For Android and iOS clients, it depends how you're developing the clients. Web clients, TTS playback can be done using HTML5 <audio>. I believe Android also supports audio recording using HTML5 extensions, but iOS does not (yet). For standard iOS and Android apps, SpeechKit is the tool of choice; it is designed for the production speech API, but can be made to work with the Mashup server as well.
On a PC/Mac client, using wget is not the recommended approach for real use because storing up all audio and then sending it introduces latency. For any real-world application, I recommend setting things up so that audio is streamed to the server in real time. This often takes a bit more work, but is much better in terms of latency.
That's it as far as the high-level overview is concerned... I'll be here to help with the specifics as well.
- Thomas

Analyze your audio with the "Swiss Army Knife" of audio analysis programs

Wavesurfer and Transcriber are available on the department computers, but in case you want to download them yourself, here are the links:

Speech Technology and Speech Recognition: AT&T Labs

http://www.youtube.com/watch?v=V0uwydE0HaA&feature=youtube_gdata

http://www.cs.washington.edu/mssi/2013/williams-2013-07-uw-msr-si.pdf
http://mi.eng.cam.ac.uk/~sjy/papers/ygtw13.pdf POMDP-based Statistical Spoken Dialogue Systems: a Review Steve Young, Fellow, IEEE, Milica Gasˇic ́, Member, IEEE, Blaise Thomson, Member, IEEE, and Jason D Williams, Member, IEEE
The Second Dialog State Tracking Challenge , 2ndDialogStateTracking.pdf, http://www.aclweb.org/anthology/W/W14/W14-4337.pdf
http://research.microsoft.com/pubs/161918/williams2009tutorial.pdf

2. Conversational vs. Broadcast News: BBN_2004_CT, BBN_2004_BN, BBN-LIMSI-iEEE06, NIST_rt04f_stt_results

4. Synchronic across major players: BBN_2004, IBM_2004, SRI_2004, NIST_rt04f_stt_results

5. Language (Chinese): BBN_2007_Mandarin, IBM 2007 Arabic, SRI-IEEE06, NIST_rt04f_stt_results

7. Application (Meeting recorder): SRI_ICSI_2007_meeting_Recorder, IBM_2007_lecture_meeting, RT07Results-v08

8. Application (Term detction): IBM STD 06sigir07, Queensland phonetic search, STD06-NIST-English_Results

Project Ouch - Outing Unfortunate Characteristics of HMMs (Used for Speech Recognition): http://www.icsi.berkeley.edu/icsi/projects/speech/ouch

http://voiceinthemachine.com/2012/07/03/whats-wrong-with-speech-recognition/