speech-recognition

问题 I would like to write a program in C# that includes limited vocabulary speech recognition of languages such as Finnish or Polish. Microsoft's Speech SDK works great for English but can it support other languages like those? If not, what other (hopefully affordable) software tools are available? 回答1: Have a look at Microsoft Server Speech Platform 10.2. It supports both STT and TTS. For 26 Languages, including Finnish and Polish! Here's a link that will get you started. http://www.codeproject

问题 I tried Speech API example for Windows Phone 8. It is working good with English language, but when I switch emulator's language setting to Russian language, speech recognition broke. On this code: // Perform speech recognition. this.recoOperation = recognizer.RecognizeAsync(); var recoResult = await this.recoOperation; It throws Exception: SPERR_WINRT_UNSUPPORTED_LANG 0x800455BC The requested language is not supported. So, It is means what Russian language is not supported with Speech

问题 I tried Speech API example for Windows Phone 8. It is working good with English language, but when I switch emulator's language setting to Russian language, speech recognition broke. On this code: // Perform speech recognition. this.recoOperation = recognizer.RecognizeAsync(); var recoResult = await this.recoOperation; It throws Exception: SPERR_WINRT_UNSUPPORTED_LANG 0x800455BC The requested language is not supported. So, It is means what Russian language is not supported with Speech

问题 I tried Speech API example for Windows Phone 8. It is working good with English language, but when I switch emulator's language setting to Russian language, speech recognition broke. On this code: // Perform speech recognition. this.recoOperation = recognizer.RecognizeAsync(); var recoResult = await this.recoOperation; It throws Exception: SPERR_WINRT_UNSUPPORTED_LANG 0x800455BC The requested language is not supported. So, It is means what Russian language is not supported with Speech

问题 I have implemented a continous speech recognizer using SpeechRecognizer. RecognitionListener generally goes to ERROR_NETWORK (Error no 2) after onBeginningOfSpeech. This occurs not every time but many times. This behaviour started since last update of Google 4.1.24.1672412.arm update (12 January 2015) protected class SpeechRecognitionListener implements RecognitionListener { public void onBeginningOfSpeech() { } public void onError(int error) { if (mIsStreamSolo) { // CAudioLibrary.unmute();

问题 I want to start a new activity that recognizes speech from the beginning and could read incoming message right after the activity started. This code is the code that merged from default. It runs well in default condition. But I want to remove the button as the trigger and use voice instead to trigger further action in SMSReaderMain.java . Therefore, I use pocketsphinx for Android to make it possible. pocketSphinxAndroidDemo-preAlpha project Android text to Speech Tutorial project It gives me

问题 I'm new to working with the Microsoft.Speech recognizer (using Microsoft Speech Platform SDK Version 11) and I'm trying to have it output the n-best recognition matches from a simple grammar, along with the confidence score for each. According to the documentation (and as mentioned in the answer to this question), one should be able to use e.Result.Alternates to access the recognized words other than the top-scoring one. However, even after resetting the confidence rejection threshold to 0

问题 I have an activity that implements RecognitionListener . To make it continuous, every time onEndOfSpeech() I start the listener again: speech.startListening(recognizerIntent); But, it takes some time (around half a second) till it starts, so there is this half a second gap, where nothing is listening. Therefore, I miss words that were spoken in that time difference. On the other hand, when I use Google's Voice input, to dictate messages instead of the keyboard - this time gap does not exist.

问题 I'm having problems in the decoding part of speech recognition. I followed the steps here. When I type: perl scripts_pl/decode/slave.pl , I get these errors: MODULE: DECODE Decoding using models previously trained Decoding 130 segments starting at 0 (part 1 of 1) Could not find executable for /home/go/Documents/tutorial/an4/bin/sphinx3_decode at /home/go/Documents/tutorial/an4/scripts_pl/decode/../lib/SphinxTrain/Util.pm line 299. Aligning results to find error rate Can't open /home/go

问题 Yes, I'm aware that speech recognition is fairly complicated (as an understatement). What I'm looking for is a method for distinguishing between maybe 20-30 phrases. An ability to split words (discrete speech is fine) would be nice, but isn't required. The software will be user-dependent(i.e. for use by me). I'm not looking for existing software, but for a good way of going about doing this myself. I've looked into various existing methods and it seems like splitting the sound into phonemes,